Viscosity cooperative control method and system in cow milk cheese mixing process

Abstract

The invention discloses a viscosity cooperative control method and system in a cow milk and cheese mixing process, and relates to the technical field of mixing control, the method comprises the following steps: heating cow milk to a target temperature, adding cheese, starting stirring to execute shearing, and performing temperature control compensation; when the mixture enters a blending stage, establishing a viscosity target trajectory, and constructing a cost function in combination with stirring rate, heating energy consumption and disturbance amplitude constraint; and optimizing the stirring speed, the heating current and the disturbance amplitude by using a cost function, controlling the stirring process, and reducing the stirring speed, the temperature and the disturbance amplitude after final-state viscosity curing is achieved to complete mixing. According to the invention, the technical problems of unstable mixing quality and relatively high energy consumption caused by dependence on fixed control parameters and incapability of accurately controlling the product viscosity in the existing cow milk mixing technology are solved, and the technical effects of ensuring the stability of the mixing process and reducing the energy consumption through cooperative control optimization based on the cost function and accurately adjusting the control parameters are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mixing control, in particular to a viscosity synergistic control method and system in the mixing process of cow milk and cheese. BACKGROUND

[0002] In dairy product production, the mixing of cow milk and cheese is one of the key processes. The traditional mixing process is usually controlled by fixed stirring speed and heating temperature, but this method often lacks flexibility and is difficult to adjust in real time according to the characteristics of different raw materials. In the prior art, most mixing control systems ignore the influence of stirring speed, temperature control and external disturbance on the mixing quality, resulting in product viscosity fluctuation, inaccurate temperature control and excessive energy consumption. In addition, the traditional method cannot effectively respond to disturbances in the production process and often relies on manual adjustment, lacking automation and precision. SUMMARY

[0003] The present application provides a viscosity synergistic control method and system in the mixing process of cow milk and cheese, to solve the technical problems that the existing cow milk mixing technology relies on fixed control parameters, cannot accurately control the product viscosity, and leads to unstable mixing quality and high energy consumption.

[0004] In a first aspect, the present application provides a viscosity synergistic control method in the mixing process of cow milk and cheese, the method comprising: after injecting cow milk into a target stirring container, heating the cow milk to a target temperature interval, and adding cheese; starting the target stirring container, performing cheese shearing based on a first stirring parameter, and configuring a linkage temperature control compensation; after detecting that the cow milk and cheese enter a structural intermingling synchronization stage, establishing a calibrated viscosity target trajectory, and establishing a cost function according to the calibrated viscosity target trajectory, stirring speed variation smoothing constraint, heating energy consumption constraint, and disturbance amplitude constraint; using the cost function to perform synergistic control optimization of stirring speed, heating current, and disturbance amplitude, and establishing a synergistic control optimization result; using the synergistic control optimization result to control the operation of the target stirring container, and after meeting the final state viscosity solidification state, reducing the stirring speed and controlling the temperature, and simultaneously reducing the disturbance amplitude of the stirring path, to complete the mixing.

[0005] In a second aspect of the present application, a viscosity synergistic control system in a cow milk cheese mixing process is provided, the system comprising: a heating control module configured to inject cow milk into a target stirring container, heat the cow milk to a target temperature range, and then add cheese; a linkage temperature control compensation configuration module configured to start the target stirring container, perform cheese shearing based on first stirring parameters, and configure linkage temperature control compensation; a cost function establishment module configured to establish a calibrated viscosity target trajectory when detecting that the cow milk cheese enters a structural intermingling synchronization stage, and establish a cost function based on the calibrated viscosity target trajectory, stirring rate variation smoothing constraints, heating energy consumption constraints, and disturbance amplitude constraints; a synergistic control optimization module configured to perform synergistic control optimization of stirring rate, heating current, and disturbance amplitude using the cost function, and establish a synergistic control optimization result; and a stirring execution module configured to control the target stirring container using the synergistic control optimization result, and after meeting a final state viscosity solidification state, reduce the stirring speed and the control temperature, and simultaneously reduce the disturbance amplitude of the stirring path to complete the mixing.

[0006] One or more technical solutions provided in the present application have at least the following technical effects or advantages: The viscosity synergistic control method and system in a cow milk cheese mixing process provided by the present application relate to the technical field of mixing control. The synergistic control of stirring rate, heating current, and disturbance amplitude is optimized by establishing a cost function. The control parameters in the mixing process are adjusted in real time using a feedback mechanism. After the final state viscosity is solidified, the stirring speed and the temperature are reduced to complete the mixing. The technical problem of unstable mixing quality and high energy consumption caused by the dependence of existing cow milk mixing technology on fixed control parameters and the inability to accurately control product viscosity is solved. The technical effect of accurately adjusting the control parameters by synergistic control optimization based on the cost function is achieved to ensure the stability of the mixing process and reduce energy consumption. BRIEF DESCRIPTION OF DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0008] Figure 1 The viscosity synergistic control method in a cow milk cheese mixing process provided by the present application is shown in the flowchart. Figure 2 The viscosity synergistic control system structure in a cow milk cheese mixing process provided by the present application is shown in the structural diagram.

[0009] The reference signs are explained as follows: heating control module 11, linkage temperature control compensation configuration module 12, cost function establishment module 13, collaborative control optimization module 14, and stirring execution module 15. DETAILED DESCRIPTION

[0010] The present application provides a viscosity collaborative control method and system in the mixing process of cow milk and cheese, which is used to solve the technical problems that the existing cow milk mixing technology relies on fixed control parameters, cannot accurately control the product viscosity, and leads to unstable mixing quality and high energy consumption.

[0011] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0012] It should be noted that the terms "first", "second", and the like in the specification and the above drawings of the present application are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0013] Embodiment one, as shown in the present application, provides a viscosity collaborative control method in the mixing process of cow milk and cheese, which comprises: Figure 1 P10: After injecting cow milk into the target stirring container, the cheese is put into the target stirring container when the cow milk is heated to the target temperature interval.

[0014] Specifically, first, the cow milk is injected into the target stirring container. The target stirring container is a device specially designed for mixing cow milk and cheese, which usually has good sealing performance and high-efficiency heat conduction performance to ensure the uniformity and temperature control of the mixing process. In order to ensure the stability and accuracy of the subsequent mixing, the inner wall of the container is often equipped with a heating system, such as an electric heating wire or a hot water circulation system, which can provide uniform temperature distribution during the heating process.

[0015] ​Next, the milk needs to be heated to a target temperature range, which is determined according to the melting and reaction temperature of the cheese. The goal of the heating process is to bring the milk temperature to an appropriate range without damaging the properties of the cheese, so that the subsequent cheese feeding and mixing reaction can be carried out. Generally, the temperature of the milk is monitored by a temperature sensor, and if the temperature is lower than the set value, the heating system will automatically start to raise the temperature of the milk by electric heating or hot water circulation; when the temperature reaches the predetermined range, the heating system will automatically adjust or stop to ensure that the milk always remains in the target temperature range.

[0016] When the milk is heated to the target temperature range, the cheese should be fed in a timely manner. The amount and time of cheese addition need to be accurately controlled according to the temperature of the milk and the requirements of the target product. Too early or too late feeding of the cheese will affect the mixing effect. Generally, the cheese should be fed immediately after the temperature of the milk stabilizes, which can ensure that the cheese can quickly absorb moisture and blend into the milk at the appropriate temperature. The interaction between the cheese and the milk will accelerate at a certain temperature, and too high a temperature will cause changes in the structure of the cheese, affecting the texture of the final product, while too low a temperature may cause the cheese to be difficult to mix with the milk, affecting its taste and flavor.

[0017] Therefore, during this process, real-time monitoring and adjustment of the temperature using an automatic temperature control system is the key to ensuring the stability of the heating process. Temperature setting and adjustment can use a PID control algorithm to minimize temperature error. At this time, the stirring system in the stirring container will also be started simultaneously, adjusting the stirring speed according to the reaction characteristics of the milk and cheese to avoid splashing of cheese particles or uneven mixing caused by too fast stirring. The stirring process not only promotes the physical fusion of the cheese and milk, but also ensures uniform temperature distribution, so that the reaction achieves the desired effect.

[0018] P20: Start the target stirring container, perform cheese shearing based on the first stirring parameter, and configure a linkage temperature control compensation.

[0019] Further, the step P20 of the embodiments of the present application further comprises: P21: input the first stirring parameter and the target temperature range as input data into a temperature loss analysis model, perform stirring temperature loss fitting under the target temperature range, and output the fitting result; P22: configure a linkage temperature control compensation according to the fitting result.

[0020] Optionally, the target stirring container is started, and the cheese is sheared based on the preset first stirring parameter, and a linkage temperature control compensation is configured to maintain temperature stability during the mixing process.

[0021] First, the target stirring container is started, and the stirring speed and stirring mode are adjusted according to the preset first stirring parameters. The first stirring parameters are optimized based on experiments and production experience, aiming to achieve effective shearing and dispersion of cheese in cow's milk, thereby promoting the uniform mixing of cheese. During stirring, the shearing action of cheese helps to break and reform its structure, which is crucial for the texture and taste of the final product.

[0022] While stirring, the first stirring parameters and the target temperature range are input into the temperature loss analysis model as input data. This model is used to simulate and analyze the possible temperature loss during stirring under specific stirring parameters and target temperature range. By performing stirring temperature loss fitting under the target temperature range, the model can output the fitting results, i.e., the actual temperature changes during stirring.

[0023] According to the fitting results, configure the linkage temperature control compensation. Linkage temperature control compensation is a dynamic temperature control strategy that automatically adjusts the output of the heating system according to the actual temperature changes during stirring to compensate for temperature loss, thereby maintaining temperature stability during mixing. This compensation mechanism helps to avoid problems such as uneven mixing of cheese or unstable product quality caused by temperature fluctuations.

[0024] The key to this process is real-time and precision, through continuous monitoring and feedback adjustment to ensure the stability of the stirring process, thereby ensuring that the mixing of cheese and cow's milk reaches the expected taste and quality standards.

[0025] Further, the step P20 of the embodiments of the present application further includes: P22-1: Establish a collection feedback cycle node, activate the distributed temperature sensor at the collection feedback cycle node, perform temperature field collection of the target stirring container, and establish a cycle node temperature field feedback; P22-2: Perform compensation adaptive correction management of linkage temperature control compensation according to the cycle node temperature field feedback.

[0026] Specifically, the temperature control compensation system can be further optimized through precise temperature monitoring and feedback mechanisms to ensure more accurate and adaptive temperature control in the stirring container.

[0027] Firstly, one or more collection feedback cycle nodes are established, which are preset time points or specific stages of the mixing process, at which the distributed temperature sensors will be activated. The temperature sensors provide real-time temperature data feedback by precisely measuring the temperature at different locations within the mixing container. At each collection feedback cycle node, the temperature sensors perform temperature field collection of the target mixing container, ensuring accurate monitoring of temperature distribution in each area. Temperature field collection is achieved by simultaneously monitoring temperature changes at different locations within the container using multiple distributed temperature sensors, generating a complete temperature distribution map. This temperature distribution map is obtained through real-time feedback of sensor data, which can help determine whether there are excessively high or low temperatures during the mixing process, and thus optimize the heat distribution during the mixing process.

[0028] The collected temperature data is used to establish periodic node temperature field feedback, which means that the temperature data at each collection node is recorded and used to analyze the temperature distribution and trends within the mixing container. The temperature field feedback of the periodic node can provide time series data of temperature changes, allowing the system to understand the temperature conditions at each location at each time. These data will be used as input for the linkage temperature control compensation, helping the system to adjust the heating power and temperature regulation strategy in real time to ensure that the target temperature range is maintained during the mixing process.

[0029] Next, according to the temperature field feedback of the periodic node, compensation adaptive correction management of the linkage temperature control compensation is carried out. The core of this process is to automatically adjust and optimize the compensation strategy through real-time analysis of the temperature field feedback data. When the temperature sensor detects that the temperature of a certain area deviates from the target temperature range, the system will adaptively correct the temperature control parameters based on the feedback data, such as adjusting the power output of the heating system, increasing or decreasing the heating time, or optimizing the heat distribution method, to ensure that the temperature distribution during the entire mixing process is stable within the set target range.

[0030] The advantage of this compensation adaptive correction management is its high automation and precision. The system can dynamically adjust the compensation strategy based on real-time collected temperature field data to avoid the impact of manual intervention or preset parameter failure.

[0031] P30: When it is detected that the milk cheese enters the structural intermingling synchronization stage, a calibration viscosity target trajectory is established, and a cost function is established based on the calibration viscosity target trajectory, the stirring rate variation smoothing constraint, the heating energy consumption constraint, and the disturbance amplitude constraint.

[0032] wherein the cost function is as follows: wherein, represents the cost function, represents a dimensionless time, and [0, 1] is a normalized time axis, the normalized actual viscosity, characterizing the normalized target viscosity trajectory in time , the normalized stirring rate, characterizing the stirring rate variation smoothness, the normalized heating current, the normalized stirring path perturbation amplitude, respectively the stirring rate variation penalty weight, the electrical energy consumption penalty weight, the perturbation amplitude penalty weight.

[0033] It should be understood that when the mixing process of milk and cheese enters the structural intermingling synchronization phase, i.e. the two ingredients begin to mix uniformly and form a stable structure, the system will establish a calibration viscosity target trajectory. This target trajectory is pre-set based on the quality requirements of the product and the production process parameters, and it defines the ideal viscosity variation curve within the normalized time axis [0, 1].

[0034] Next, according to the calibration viscosity target trajectory, a cost function is established, as shown in the above formula, which consists of four parts: the viscosity error term, the stirring rate variation smoothness constraint term, the heating energy consumption constraint term and the perturbation amplitude square term. This function takes into account factors such as stirring rate variation smoothness, heating energy consumption and stirring path perturbation amplitude, in order to achieve optimal control of the mixing process.

[0035] Specifically, first, a dimensionless time is introduced, which is defined as: = ; where and are the starting and ending times on the actual time axis, respectively. In this way, the actual time is converted to dimensionless time, which makes the optimization process independent of the specific time length, suitable for a unified control framework for any batch or product.

[0036] Next, the first component of the cost function, the viscosity error term, is established, which is expressed as: , the purpose of which is to minimize the difference between the actual viscosity and the target viscosity. During the mixing process, the actual viscosity changes over time, while the target viscosity trajectory is the ideal result of mixing milk and cheese. By integrating the square of the difference between the two, the cost function will tend to adjust the actual viscosity as close as possible to the target viscosity, thereby ensuring that the mixing process reaches the expected consistency.

[0037] The second part is the stirring rate variation smoothness constraint term: The stirring rate throughout the mixing process will affect the mixing effect, and too fast or too slow rate changes can lead to uneven mixing or incomplete reaction of milk and cheese. Therefore, by controlling the rate of change of stirring rate, ensure that the stirring rate changes smoothly, so as to avoid uneven mixing or excessive shear caused by sharp changes in rate.

[0038] Next, the heating energy consumption constraint term is established: , to ensure that the energy consumed during mixing is minimized. The heating system plays a crucial role in the mixing of milk and cheese, and too high or too low temperature can affect the structure of cheese and the quality of the final product. By controlling the heating current and minimizing its square sum, the cost function aims to reduce unnecessary energy consumption while ensuring that the heating temperature of the milk remains within a reasonable range.

[0039] Finally, the disturbance amplitude constraint term is established: , to control the external disturbances that may occur during stirring. During the mixing process, external factors such as equipment instability, temperature fluctuations, etc. may cause disturbances to the stirring path, which can affect the uniformity of the mixing. By limiting the size of the disturbance amplitude, the cost function can ensure the stability and consistency of the stirring process, ensuring the complete fusion of milk and cheese.

[0040] The optimization of the cost function balances the priority of different goals by adjusting the weight of each constraint. Specifically, the penalty weights of stirring rate change smoothness, heating energy consumption and disturbance amplitude determine their importance in the optimization process. For example, if the weight of heating energy consumption is set to be larger, the system will pay more attention to reducing energy consumption, ensuring that the heating power is used reasonably; if the penalty weight of disturbance amplitude is increased, the system will pay more attention to the stability and consistency of the stirring process.

[0041] To ensure that the temperature and mixing effect during stirring meet the target, the heating current and stirring rate can also be adjusted in real time through feedback. Specifically, temperature sensors will continuously monitor the temperature inside the container and input the temperature data into the control system for analysis. According to the feedback results, the control system will automatically adjust the power output of the heating device to ensure that the temperature always remains within the target interval.

[0042] Through this optimization process based on the cost function, the system can find the best balance between various control constraints, ensuring that the mixing process of milk and cheese not only meets the viscosity target, but also effectively controls the stirring rate, heating energy consumption and disturbance amplitude, ultimately achieving the ideal mixing effect and efficient energy use.

[0043] P40: Use the cost function to perform collaborative control optimization of stirring rate, heating current, and disturbance amplitude, and establish the collaborative control optimization results.

[0044] Further, the step P40 of the embodiments of the present application further comprises: P41: establishing a control data source, wherein the control data source comprises a local data source and an online data source, and the local data source and the online data source are provided with a basic trust identifier; P42: screening according to the basic trust identifier and a data effect identifier of the control data source to construct an initial population; P43: performing fitness evaluation on each candidate solution in the initial population by using the cost function to establish a fitness evaluation result; and P44: performing cross variation iteration according to the fitness evaluation result to complete collaborative control optimization according to a cross variation iteration result.

[0045] Specifically, the cost function is used to perform collaborative control optimization on the stirring rate, heating current and disturbance amplitude, and a collaborative control optimization result is established.

[0046] Firstly, a control data source is established, which comprises a local data source and an online data source. The local data source can include historical production data, experimental data, etc., and the online data source can include real-time monitoring data, remote databases, etc. In order to ensure the reliability and effectiveness of the data, the local data source and the online data source are both provided with a basic trust identifier. These trust identifiers can be evaluated based on the reliability of the data source, the accuracy and integrity of the data, etc.

[0047] Then, screening is performed according to the basic trust identifier and a data effect identifier of the control data source to construct an initial population. The data effect identifier is an evaluation of the quality of the data and the credibility of the data source. According to these identifiers, the system can identify which data has the greatest contribution to the optimization process, and select appropriate data for screening. In this way, an initial population is constructed, which contains different candidate solutions representing different combinations of stirring rate, heating current and disturbance amplitude.

[0048] Further, fitness evaluation is performed on each candidate solution in the initial population by using the cost function to establish a fitness evaluation result. Fitness evaluation is completed by calculating the performance of each candidate solution in the cost function. Candidate solutions with good performance will have a higher fitness score. The fitness score directly reflects the optimization degree of the control scheme on the target (such as viscosity, temperature control, mixing stability, etc.) in the actual mixing process. In this way, the advantages and disadvantages of each candidate solution can be quantified, providing data support for subsequent optimization.

[0049] Finally, crossover and mutation iterations are performed based on the fitness evaluation results. This operation, based on a genetic algorithm, generates new candidate solutions by combining and mutating candidate solutions with higher fitness. These new candidate solutions are further optimized in subsequent iterations until the optimal control strategy is found. Through this iterative process of crossover and mutation, the optimal solution can be searched across a wider parameter space, ultimately achieving the optimal coordinated control strategy. Ultimately, the optimal control combination of stirring rate, heating current, and disturbance amplitude is determined, ensuring that each objective in the milk and cheese mixing process can be achieved efficiently and stably.

[0050] Furthermore, the crossover and mutation iteration is performed according to the fitness evaluation result. In the embodiment of the present application, step P44 further includes: P44-1: Divide the initial population into sub-populations and establish partition identifiers, which include stirring rate optimization sub-population, heating current optimization sub-population, and disturbance amplitude control sub-population; P44-2: Determine whether the number of iterations meets the dynamic interaction cycle. If the number of iterations meets the dynamic interaction cycle, use the partition identifier to share the optimal solution within the sub-population partition; P44-3: Complete cross-mutation iteration based on the population sharing result.

[0051] Optionally, the crossover-mutation iteration process can be further refined to improve the efficiency and effectiveness of collaborative control optimization. Specifically, the crossover-mutation iteration process divides the population into multiple subpopulations and shares and optimizes the optimal solution within these subpopulations, thereby gradually improving the fitness of the population.

[0052] First, the initial population is partitioned into subpopulations, and a partition identifier is established for each subpopulation. This partitioning allows the optimization process to more precisely and independently optimize different control variables. Specifically, the initial population is divided into three subpopulations: a stirring rate optimization subpopulation, a heating current optimization subpopulation, and a disturbance amplitude control subpopulation. Each subpopulation is responsible for a specific control objective. For example, the stirring rate optimization subpopulation focuses on optimizing the range of stirring rate variation, the heating current optimization subpopulation focuses on optimizing the efficiency of heating current utilization, and the disturbance amplitude control subpopulation is responsible for controlling disturbances during the stirring process. This partitioning method allows each control objective to be optimized independently, thereby improving the efficiency and accuracy of the optimization process.

[0053] Next, it is determined whether the number of iterations has met the requirements of the dynamic interaction period, i.e., whether a sufficient number of iterations has passed. In the optimization process, the dynamic interaction period is a control threshold that determines how many iterations pass before the system performs information exchange between subpopulations. If the number of iterations meets the dynamic interaction period, the system will share optimal solutions within the subpopulations using the partition identifier. Through sharing, the optimal solution in each subpopulation is passed to other subpopulations, enabling each subpopulation to use the optimal solution information of other subpopulations for further optimization. This process helps to improve the overall fitness of the population while avoiding local optimal solutions and promoting the discovery of global optimal solutions.

[0054] Finally, based on the population sharing results, cross-variation iterations are completed. Specifically, the cross-variation operation will combine optimal solutions in different subpopulations and perform mutation based thereon to generate new candidate solutions. These new candidate solutions will enter the next round of evaluation and optimization process. Through continuous cross-variation iterations, a more optimal control strategy is sought in a wider parameter space, ultimately enabling the combination of the three control parameters of stirring rate, heating current, and perturbation amplitude to reach an optimal state, ensuring that each target in the mixing process of cow milk and cheese is effectively achieved to optimize the stability, efficiency, and energy consumption of the mixing process.

[0055] Further, the step P44-3 of the embodiment of the present application further includes: P44-31: setting a perturbation protection coefficient and a fusion ratio of shared solutions; and P44-32: performing cross-variation iterations after the population sharing results are constrained according to the perturbation protection coefficient and the fusion ratio.

[0056] In a possible embodiment of the present application, the constraint of the population sharing results can be optimized by setting a perturbation protection coefficient and a fusion ratio of shared solutions, and cross-variation iterations are performed.

[0057] Before the population sharing is performed, the perturbation protection coefficient and the fusion ratio of shared solutions are first set. The perturbation protection coefficient is used to control the influence of the optimal solution shared from other subpopulations on the genetic diversity of the current subpopulation. By adjusting the perturbation protection coefficient, the genetic diversity of the current subpopulation can be protected, preventing the shared solution from causing excessive perturbation to the existing population structure, thereby avoiding premature convergence to a local optimal solution. Meanwhile, the fusion ratio is used to control the degree of fusion of the shared solution and the solution of the current subpopulation. A higher fusion ratio means that a higher proportion of shared solutions will be used in the cross-variation process, thereby more strongly promoting the fusion of different subpopulations. A lower fusion ratio may maintain the independence between subpopulations. By setting a reasonable fusion ratio, the relationship between individualized optimization and global optimization of subpopulations can be balanced, avoiding premature convergence or the occurrence of local optimal solutions.

[0058] Next, according to the set disturbance protection coefficient and fusion ratio, the population sharing result is constrained to ensure that the sharing solution does not bring too much disturbance. After the constraint, cross variation iteration is performed again, that is, while retaining the core information of the sharing solution, excessive disturbance is avoided to affect the optimization result. The cross variation operation generates new solutions by selecting and mixing multiple candidate solutions, and these new solutions will be used for fitness evaluation in the next round. Through the sharing solution after the constraint and cross variation, the system can efficiently optimize the control variables such as stirring rate, heating current and disturbance amplitude while ensuring the stability of the mixing process and the balance of each target.

[0059] By introducing the disturbance protection coefficient and the fusion ratio, the efficiency and effect of collaborative control optimization can be further improved. Not only can the quality and consistency of the final product be ensured, but also the production efficiency can be improved and the production cost can be reduced by accurately controlling the energy consumption and disturbance in the stirring process.

[0060] Further, the cross variation iteration according to the fitness evaluation result comprises the following steps: P44-1a: Establish a preset iteration period and configure a variation attenuation factor mapped with the preset iteration period; P44-2a: Perform matching reconstruction of the preset iteration period according to the real iteration state, and set dynamic compensation of the matching variation attenuation factor according to the matching reconstruction result; P44-3a: After compensating the matching variation attenuation factor according to the dynamic compensation, perform cross variation iteration.

[0061] Specifically, in the further refinement process, the preset iteration period, the variation attenuation factor and the dynamic compensation thereof can be introduced to further optimize the cross variation iteration process, so as to improve the global optimization ability and stability of the population.

[0062] Firstly, a preset iteration period is established, which refers to that after a certain number of iterations in the whole optimization process, the system will re-optimize the parameters. The preset iteration period is set to control the frequency of cross variation process and provide appropriate adjustment time for variation operation, so that the optimization process can be effectively adjusted at different stages. At the same time, a variation attenuation factor is configured for each preset iteration period, which is used to control the disturbance amplitude in each cross variation. With the increase of the number of iterations, the variation attenuation factor will gradually decrease, ensuring that in the later stage of optimization, the system tends to be stable, avoiding excessive disturbance affecting the search for optimal solution.

[0063] Then, the matching reconstruction of the preset iteration period is performed according to the real iteration state, that is, the suitability of the preset iteration period is dynamically adjusted by analyzing the current optimization progress and iteration state. If the optimization progress is faster at some stages, the iteration period is adjusted so that the crossover and mutation process can be performed in a shorter period. Conversely, if the optimization progress is slower, the iteration period can be extended to give the optimization process more adjustment time. After the matching reconstruction of the iteration period, a dynamic compensation of the matching mutation attenuation factor can also be set according to the matching reconstruction result. This dynamic compensation mechanism can adjust the mutation attenuation factor according to the actual iteration effect, ensuring that the mutation attenuation factor always remains within a reasonable range during the optimization process, thereby ensuring the efficiency and stability of the crossover and mutation.

[0064] Finally, after the matching mutation attenuation factor is compensated according to the above dynamic compensation, the crossover and mutation iteration is performed. Specifically, the mutation attenuation factor adjusted by the dynamic compensation will affect the next round of crossover and mutation operation, control the size of the mutation amplitude, and ensure that the optimization process gradually converges in the later iterations and avoid excessive disturbance to interfere with the formation of the optimal solution. Through this adjustment of the mutation attenuation factor based on dynamic compensation, the system can flexibly control the disturbance amplitude at different iteration stages to achieve efficient optimization while ensuring the stability and global search ability of the optimization process.

[0065] Through this series of dynamic adjustment of the iteration period and the mutation attenuation factor, the system can more effectively balance local optimization and global optimization, avoid excessive disturbance leading to premature convergence or falling into a local optimal solution, and thus ensure that the three control variables of stirring rate, heating current and disturbance amplitude can finally achieve the optimal combination.

[0066] P50: The target stirring container is controlled to work using the cooperative control optimization result, and after the final state viscosity solidification state is met, the stirring speed and the control temperature are reduced, and the disturbance amplitude of the stirring path is simultaneously reduced, and the mixing is completed.

[0067] Further, the step P50 of the embodiment of the present application further comprises: P51: The mixing result is identified for mixing quality, and a mixing quality identification mark is established; P52: After the mixing quality identification mark and the cooperative control optimization result are mapped, they are stored to a processing database, and the local data source is updated by the processing database.

[0068] It should be understood that the target stirring container is controlled to work using the aforementioned cooperative control optimization result. That is, based on the optimal solution optimized by the cost function, the stirring container is controlled to perform the mixing task according to the optimized parameters, ensuring that the viscosity, temperature and stirring rate, etc. are maintained within the ideal range during the mixing process.

[0069] When the mixing process reaches the predetermined mixing requirements, it enters the final viscosity solidification state. This state refers to the viscosity of the mixture having reached the expected target, indicating that the mixing process has been completed and the physical properties are stable. At this time, excessive stirring or high temperature can be avoided by reducing the stirring speed and controlling the temperature, ensuring that the quality of the final product is not affected by excessive processing. In addition, the disturbance amplitude of the stirring path is reduced synchronously, reducing the influence of external disturbances on the mixture, further stabilizing the mixing result and completing the entire mixing process.

[0070] Next, the mixing result is identified for mixing quality, and a mixing quality identification mark is established. Mixing quality identification includes detecting and evaluating key quality indicators such as viscosity, texture, and taste of the final product. Through these detections, it can be determined whether the mixing process has reached the expected quality standards, and these information is converted into a mixing quality identification mark.

[0071] Further, the mixing quality identification mark is mapped with the collaborative control optimization result, that is, the quality evaluation result obtained in each mixing process is associated with the optimization control parameters used (such as stirring speed, heating current, disturbance amplitude, etc.). This mapping relationship will be stored in the processing database and updated through the local data source, so that the system can refer to historical data during the next optimization, improving control accuracy and efficiency. In this way, the system can continuously learn and improve the control strategy to ensure that in subsequent mixing processes, the control parameters can be optimized according to historical experience, further improving production efficiency and product quality.

[0072] In this way, the present application not only can realize accurate control in the current production batch, but also can improve the control accuracy and product quality of future production batches through continuous learning and optimization, ensuring that the quality of each mixing reaches the best standard, while improving the automation level of production and the efficiency of data utilization.

[0073] In summary, the embodiments of the present application have at least the following technical effects: The present application uses a cost function optimization strategy to dynamically balance viscosity trajectory tracking, energy consumption constraints, and stirring stability requirements, to achieve collaborative control of stirring speed, heating current, and disturbance amplitude in the mixing process of cow milk and cheese, improving the control accuracy of the mixing process and ensuring process adjustability and controllability. The use of sub-population division and cross-variation mechanism improves the efficiency of multi-variable parameter optimization. The introduction of disturbance protection coefficient and fusion ratio manages the disturbance control in the population sharing process. By establishing a mixing quality identification mark and mapping it with the control result, a closed-loop association between control parameters and quality results is achieved. Combined with the iterative cycle mapping and dynamic compensation mechanism of variation attenuation factor, the optimization intensity is adjusted adaptively to enhance the stability and convergence of the optimization process.

[0074] The technical effects of optimizing through cost function-based collaborative control, accurately adjusting control parameters, ensuring stability of the mixing process, and reducing energy consumption are achieved.

[0075] Embodiment two, based on the same inventive concept as the viscosity collaborative control method in the milk cheese mixing process in the preceding embodiments, as Figure 2 shown, the present application provides a viscosity collaborative control system in the milk cheese mixing process, and the system and method embodiments in the present application are based on the same inventive concept. Among them, the system comprises: A heating control module 11, which is used to put cheese when heating the milk to the target temperature interval after injecting the milk into the target stirring container.

[0076] A linkage temperature control compensation configuration module 12, which is used to start the target stirring container, perform cheese shearing based on the first stirring parameter, and configure linkage temperature control compensation.

[0077] A cost function establishment module 13, which is used to establish a calibrated viscosity target trajectory when detecting that the milk cheese enters the structural intermingling synchronization stage, and establish a cost function according to the calibrated viscosity target trajectory, stirring rate variation smoothing constraint, heating energy consumption constraint, and disturbance amplitude constraint.

[0078] A collaborative control optimization module 14, which is used to perform collaborative control optimization of stirring rate, heating current, and disturbance amplitude using the cost function, and establish a collaborative control optimization result.

[0079] A stirring execution module 15, which is used to control the target stirring container using the collaborative control optimization result, and reduce the stirring speed and control temperature after meeting the terminal state viscosity solidification state, and simultaneously reduce the disturbance amplitude of the stirring path to complete the mixing.

[0080] Further, the linkage temperature control compensation configuration module 12 is further used to perform the following steps: The first stirring parameter and the target temperature interval are input as input data into a temperature loss analysis model, a stirring temperature loss fitting under the target temperature interval is performed, and a fitting result is output; and the linkage temperature control compensation is configured according to the fitting result.

[0081] Further, the linkage temperature control compensation configuration module 12 is further used to perform the following steps: A collection feedback cycle node is established, the distributed temperature sensor is activated at the collection feedback cycle node, the temperature field collection of the target stirring container is performed, and the cycle node temperature field feedback is established; and the compensation adaptive correction management of the linkage temperature control compensation is performed according to the cycle node temperature field feedback.

[0082] Further, the cost function establishing module 13 is further used to perform the following steps: The cost function is as follows: ; wherein, characterizes the cost function, characterizes the dimensionless time, [0, 1] is the normalized time axis, is the normalized actual viscosity, characterizes the value of the normalized target viscosity trajectory at time , is the normalized stirring rate, characterizes the stirring rate change rate, which is used to control the stirring rate variation smoothness, is the normalized heating current, is the normalized stirring path disturbance amplitude, are the stirring rate change penalty weight, the electric energy consumption penalty weight, and the disturbance amplitude penalty weight, respectively.

[0083] Further, the collaborative control optimization module 14 is further used to perform the following steps: Establish a control data source, the control data source includes a local data source and an online data source, and the local data source and the online data source are provided with a basic trust identifier; according to the basic trust identifier and the data effect identifier of the control data source, an initial population is constructed; the fitness of each candidate solution in the initial population is evaluated by using the cost function, and a fitness evaluation result is established; according to the fitness evaluation result, cross variation iteration is performed, and collaborative control optimization is completed according to the cross variation iteration result.

[0084] Further, the collaborative control optimization module 14 is further used to perform the following steps: The initial population is divided into sub-populations, and a partition identifier is established, the partition identifier includes a stirring rate optimization sub-population, a heating current optimization sub-population, and a disturbance amplitude control sub-population; it is judged whether the iteration number meets the dynamic interaction period, if the iteration number meets the dynamic interaction period, the optimal solution in the sub-population partition is shared by using the partition identifier; cross variation iteration is completed according to the population sharing result.

[0085] Further, the collaborative control optimization module 14 is further used to perform the following steps: The disturbance protection coefficient and the fusion ratio of the shared solution are set; after the population sharing result is constrained according to the disturbance protection coefficient and the fusion ratio, cross variation iteration is performed.

[0086] Further, the collaborative control optimization module 14 is further used to perform the following steps: Establish a preset iteration cycle and configure a variation attenuation factor mapped to the preset iteration cycle; perform matching reconstruction of the preset iteration cycle according to the actual iteration state, and set dynamic compensation of the matching variation attenuation factor according to the matching reconstruction result; after compensating the matching variation attenuation factor according to the dynamic compensation, perform cross-mutation iteration.

[0087] Furthermore, the stirring execution module 15 is further configured to execute the following steps: Perform hybrid quality identification on the hybrid result and establish a hybrid quality identification identifier; establish a mapping between the hybrid quality identification identifier and the collaborative control optimization result, store them in a processing database, and use the processing database to update the local data source.

[0088] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0089] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0090] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A method for collaboratively controlling viscosity during the mixing process of milk and cheese, characterized in that: The method comprises: After milk is poured into the target mixing container, cheese is added when the milk is heated to the target temperature range; Start the target mixing container, perform cheese shearing based on the first mixing parameter, and configure linkage temperature control compensation; When the detected milk cheese enters the structural blending synchronization stage, a calibrated viscosity target trajectory is established, and a cost function is established based on the calibrated viscosity target trajectory, stirring rate change smoothness constraint, heating energy consumption constraint, and disturbance amplitude constraint; Using the cost function to perform collaborative control optimization of the stirring rate, heating current, and disturbance amplitude, and establishing a collaborative control optimization result; The collaborative control optimization results are used to control the operation of the target stirring container. After the final viscosity solidification state is met, the stirring speed and temperature are reduced, and the disturbance amplitude of the stirring path is simultaneously reduced to complete the mixing.

2. The method for coordinating viscosity control during the mixing process of milk cheese according to claim 1, characterized in that: The cost function is as follows: ； in, Representation cost function, Represents dimensionless time, [0,1] is the normalized time axis, is the actual viscosity after normalization, Characterize the normalized target viscosity trajectory in time The value of is the normalized stirring rate, Characterizes the stirring rate change, used to control the smoothness of stirring rate changes, is the normalized heating current, is the normalized stirring path disturbance amplitude, They are the penalty weights for stirring rate change, power consumption, and disturbance amplitude, respectively.

3. The method for coordinating viscosity control during the mixing process of milk cheese according to claim 1, characterized in that: The method of using the cost function to perform collaborative control optimization of the stirring rate, heating current, and disturbance amplitude, and establishing a collaborative control optimization result, includes: Establishing a control data source, wherein the control data source includes a local data source and an online data source, and the local data source and the online data source are provided with a basic trust identifier; Screening is performed based on the basic trust identifier and the data effect identifier of the control data source to construct an initial population; Performing fitness evaluation on each candidate solution in the initial population using the cost function to establish a fitness evaluation result; A crossover and mutation iteration is performed according to the fitness evaluation result, and a collaborative control optimization is completed according to the crossover and mutation iteration result.

4. The method for coordinating viscosity control during the mixing process of milk cheese according to claim 3, characterized in that: The performing crossover mutation iteration according to the fitness evaluation result includes: Partitioning the initial population into subpopulations and establishing partition identifiers, wherein the partition identifiers include a stirring rate optimization subpopulation, a heating current optimization subpopulation, and a disturbance amplitude control subpopulation; Determine whether the number of iterations meets the dynamic interaction period. If the number of iterations meets the dynamic interaction period, use the partition identifier to perform population sharing on the optimal solution within the subpopulation partition. Complete crossover and mutation iterations based on population sharing results.

5. The method for coordinating viscosity control during the mixing process of milk cheese according to claim 4, characterized in that: The crossover mutation iteration is completed according to the population sharing result, including: Set the disturbance protection coefficient and fusion ratio of the shared solution; After constraining the population sharing result according to the disturbance protection coefficient and the fusion ratio, crossover and mutation iterations are performed.

6. The method for coordinating viscosity control during the mixing process of milk cheese according to claim 3, wherein: The performing crossover mutation iteration according to the fitness evaluation result further includes: Establish a preset iteration cycle and configure a variation attenuation factor mapped to the preset iteration cycle; Perform matching reconstruction of a preset iteration cycle according to the actual iteration state, and set dynamic compensation of the matching variation attenuation factor according to the matching reconstruction result; After compensating the matched mutation attenuation factor according to the dynamic compensation, cross-mutation iterations are performed.

7. The method for coordinating viscosity control during the mixing process of milk cheese according to claim 1, wherein: The method of starting the target stirring container, performing cheese shearing based on the first stirring parameter, and configuring linkage temperature control compensation includes: Input the first stirring parameter and the target temperature range as input data into the temperature loss analysis model, perform stirring temperature loss fitting under the target temperature range, and output the fitting result; Configure linkage temperature control compensation according to the fitting results.

8. The method for coordinating viscosity control during the mixing process of milk cheese according to claim 7, characterized in that: Configuring linkage temperature control compensation according to the fitting result includes: Establishing an acquisition feedback cycle node, activating a distributed temperature sensor at the acquisition feedback cycle node, performing temperature field acquisition of a target stirring container, and establishing cycle node temperature field feedback; Compensation adaptive correction management of linked temperature control compensation is performed according to the temperature field feedback of the periodic nodes.

9. The method for coordinating viscosity control during the mixing process of milk cheese according to claim 1, wherein: After the final viscosity solidification state is met, the stirring speed is reduced, the temperature is controlled, and the disturbance amplitude of the stirring path is simultaneously reduced to complete the mixing, including: Conduct mixed quality identification on the mixed results and establish a mixed quality identification mark; After mapping is established between the hybrid quality identification mark and the collaborative control optimization result, the mapping is stored in a processing database, and the local data source is updated with the processing database.

10. A coordinated viscosity control system for milk and cheese mixing, characterized in that: The system comprises: A heating control module is used to inject milk into a target stirring container, heat the milk to a target temperature range, and then add cheese; a linked temperature control compensation configuration module, the linked temperature control compensation configuration module being used to start a target mixing container, perform cheese shearing based on a first mixing parameter, and configure linked temperature control compensation; A cost function establishment module, wherein the cost function establishment module is used to establish a calibrated viscosity target trajectory after detecting that the milk cheese enters the structural blending synchronization stage, and establish a cost function based on the calibrated viscosity target trajectory, a stirring rate change smoothness constraint, a heating energy consumption constraint, and a disturbance amplitude constraint; A collaborative control optimization module, wherein the collaborative control optimization module is used to perform collaborative control optimization of the stirring rate, heating current, and disturbance amplitude using the cost function, and establish a collaborative control optimization result; A stirring execution module is used to control the operation of the target stirring container using the collaborative control optimization results, and after meeting the final viscosity solidification state, reduce the stirring speed and control the temperature, and simultaneously reduce the disturbance amplitude of the stirring path to complete the mixing.

Images