Goat milk powder production process parameter self-optimization regulation and control method and system

Abstract

The invention relates to an optimization regulation and control technology for goat milk powder production process parameters, in particular to a self-optimization regulation and control method and system for the goat milk powder production process parameters. The historical production data comprises characteristic data of raw milk of historical batches, technological parameter data which are adopted for the characteristic data of the raw milk of the historical batches and cover key procedures of goat milk powder production, and retention level data of specific thermosensitive functional components in a final product produced by adopting the technological parameter data; the goat milk powder production key working procedures at least comprise a sterilization working procedure, a concentration working procedure and a drying working procedure. By recording the historical production data, obtaining the current raw material characteristics and determining the optimal historical batch based on similarity comparison and target screening, the problem that it is difficult to optimize and adjust process parameters according to raw material fluctuation and inter-process influence to improve the retention level of specific thermosensitive functional components in the prior art is effectively solved.

Description

Technical Field

[0001] The present invention relates to an optimization and control technology for goat milk powder production process parameters, and in particular to a self-optimization and control method and system for goat milk powder production process parameters. Background Art

[0002] In the production of goat milk powder, traditional processes operate based on fixed parameters (such as pasteurization, concentration, and spray drying) to ensure compliance with standards for basic nutrition, microbiological safety, and solubility. Operators primarily monitor parameter consistency. As market demand for goat milk powder quality increases, consumers are increasingly concerned about the content and activity retention of specific heat-sensitive functional ingredients (such as certain active proteins and probiotics). These high-value-added functional ingredients are extremely sensitive to heat, shear, and osmotic pressure during processing, and are easily inactivated or denatured during key steps such as sterilization, concentration, and drying. Even with strict control of conventional parameters, their retention rates remain unstable and vary significantly from batch to batch.

[0003] Production technicians attempt to improve the retention of functional ingredients by adjusting existing process parameters, such as fine-tuning sterilization temperature or time. However, this often leads to a dilemma: reducing the intensity of heat treatment may affect microbial safety, while the high temperatures of subsequent steps (such as concentration and drying) may still lead to further losses. At the same time, drastically adjusting parameters (such as lowering drying temperature) to protect sensitive ingredients may result in excessive moisture content, poor fluidity, decreased solubility, impaired storage stability, and even impact production efficiency.

[0004] Further complicating matters, the various steps in goat milk powder production aren't isolated, and parameter adjustments can trigger chain reactions. For example, changes in sterilization parameters can affect the physical properties of the milk, which in turn can impact the efficiency and effectiveness of the concentration and drying processes, ultimately affecting the particle morphology and physical properties of the milk powder. Operators rely on experience to make multi-point parameter adjustments, but often struggle to fully assess their impact on the overall process and multiple product attributes, making it difficult to find an optimal parameter combination that simultaneously balances the retention of specific functional ingredients, basic product quality, and production economics.

[0005] Companies are also trying to increase testing for specific functional ingredients in intermediate and final products, but such testing is often time-consuming and costly, making it difficult to implement high-frequency online monitoring. Delayed test results make it difficult to effectively guide traceability and adjust specific process parameters. Although a large amount of process data and product testing data has accumulated during the production process, how to systematically utilize this historical data to understand the complex relationship between process parameters and the retention rate of specific functional ingredients, and to develop a plan that covers multiple processes and can proactively optimize and adjust parameters based on raw material fluctuations to significantly improve retention rates and support continuous improvement, is a key technical challenge that needs to be solved.

[0006] In view of the above problems, the existing technology is in urgent need of improvement. Summary of the Invention

[0007] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method and system for self-optimizing and controlling process parameters of goat milk powder production.

[0008] In a first aspect, the present invention provides a method for self-optimizing and controlling process parameters of goat milk powder production, the method comprising the following steps: Recording historical production data, the historical production data including raw milk property data of historical batches, process parameter data covering key production processes of goat milk powder based on the raw milk property data of the historical batches, and retention level data of specific heat-sensitive functional ingredients in the final product produced using the process parameter data, wherein the key production processes of goat milk powder include at least a sterilization process, a concentration process, and a drying process; Obtain characteristic data of the current batch of raw milk to be produced; Based on the acquired characteristic data of the current batch of raw milk to be produced, performing a similarity comparison between the characteristic data of the current batch of raw milk to be produced and the characteristic data of raw milk of each historical batch in the recorded historical production data, to determine one or more historical batches whose characteristics match the characteristics of the current batch of raw milk to be produced; Based on the determined one or more historical batches and according to a preset retention level target for the specific heat-sensitive functional ingredient and other production constraints, at least one target historical batch is selected from the one or more historical batches, wherein the retention level data of the specific heat-sensitive functional ingredient in the final product of the target historical batch meets the preset retention level target; The process parameter data covering the key processes of goat milk powder production corresponding to at least one selected target historical batch is extracted as the recommended process parameters for the current batch of raw milk to be produced.

[0009] In a second aspect, a goat milk powder production process parameter self-optimization control system is provided, the system comprising: A data recording module for recording historical production data, the historical production data including raw milk property data of historical batches, process parameter data covering key production processes of goat milk powder based on the raw milk property data of the historical batches, and retention level data of specific heat-sensitive functional ingredients in the final product produced using the process parameter data, the key production processes of goat milk powder including at least sterilization, concentration, and drying; The current data acquisition module is used to obtain the characteristic data of the current batch of raw milk to be produced; a similarity comparison module for performing a similarity comparison between the acquired characteristic data of the current batch of raw milk to be produced and the characteristic data of each historical batch of raw milk in the recorded historical production data, so as to determine one or more historical batches whose characteristics match those of the current batch of raw milk to be produced; a target batch screening module, configured to screen at least one target historical batch from the one or more historical batches based on the determined one or more historical batches and according to a preset retention level target for the specific heat-sensitive functional ingredient and other production constraints, wherein the retention level data of the specific heat-sensitive functional ingredient in the final product of the target historical batch meets the preset retention level target; The parameter extraction module is used to extract the process parameter data covering the key processes of goat milk powder production corresponding to at least one selected target historical batch as the recommended process parameters for the current batch of raw milk to be produced.

[0010] Compared with the prior art, the present invention has the following beneficial effects: By recording historical production data, obtaining current raw material characteristics, determining the best historical batch based on similarity comparison and target screening, and extracting its process parameters as recommendations, it effectively solves the problem that existing technologies are difficult to optimize and adjust process parameters based on raw material fluctuations and inter-process influences to improve the retention level of specific thermosensitive functional ingredients. It has the advantage of being able to automatically recommend optimized process parameters based on historical data according to current raw material characteristics, thereby improving the retention level of specific thermosensitive functional ingredients, coping with raw material fluctuations, and realizing self-optimization and regulation of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 Flow chart of the method of the present invention.

[0012] Figure 2 Schematic diagram of the system structure of the present invention.

[0013] In the figure: 201, data recording module; 202, current data acquisition module; 203, similarity comparison module; 204, target batch screening module; 205, parameter extraction module. DETAILED DESCRIPTION

[0014] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention.

[0015] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0016] To this end, this application Figure 1 A method for self-optimizing and controlling process parameters of goat milk powder production is shown, which is applied to a goat milk powder production process with the goal of maximizing the retention of specific heat-sensitive functional ingredients. The method comprises the following steps: S101. Record historical production data, including raw milk property data of historical batches, process parameter data covering key production processes of goat milk powder based on the raw milk property data of historical batches, and retention level data of specific heat-sensitive functional ingredients in the final product produced using the process parameter data. The key production processes of goat milk powder include at least sterilization, concentration, and drying. S102, obtaining characteristic data of the current batch of raw milk to be produced; S103. Based on the acquired characteristic data of the current batch of raw milk to be produced, perform a similarity comparison between the characteristic data of the current batch of raw milk to be produced and the characteristic data of raw milk of each historical batch in the recorded historical production data, to determine one or more historical batches whose characteristics match the characteristics of the current batch of raw milk to be produced; S104. Based on the determined one or more historical batches, and in accordance with a preset retention level target for the specific heat-sensitive functional ingredient and other production constraints, at least one target historical batch is selected from the one or more historical batches, wherein the retention level data of the specific heat-sensitive functional ingredient in the final product of the target historical batch meets the preset retention level target; S105. Extract process parameter data covering key processes of goat milk powder production corresponding to at least one selected target historical batch as recommended process parameters for the current batch of raw milk to be produced.

[0017] Among them, historical production data refers to a collection of relevant records of past production batches, which specifically include raw milk characteristic data of historical batches, process parameter data covering the key production processes of goat milk powder based on the raw milk characteristic data of historical batches, and retention level data of specific heat-sensitive functional ingredients in the final product produced using process parameter data. Its purpose is to provide a data basis and learning samples for subsequent process parameter recommendations; raw milk characteristic data refers to data used to describe the physical, chemical or biological properties of raw milk, such as component content, microbial indicators, physical and chemical indicators, etc., whose purpose is to characterize the inherent properties of raw milk from different batches; process parameter data refers to the numerical values of various control parameters set or actually operated in the key processes of goat milk powder production, such as temperature, pressure, flow, time, etc., whose purpose is to record the processing conditions that affect the product formation process; retention level data of specific heat-sensitive functional ingredients refers to the content or activity of specific heat-sensitive functional ingredients in the final product relative to the initial content in the raw milk. or absolute value, the purpose of which is to quantify the impact of the process on the target functional ingredients; the key process in goat milk powder production refers to the core processing link that has a significant impact on the retention of specific heat-sensitive functional ingredients, including at least the sterilization process, the concentration process and the drying process, the purpose of which is to define the production scope that this method focuses on and regulates; similarity comparison refers to calculating or evaluating the degree of similarity between the characteristic data of the current batch of raw milk to be produced and the characteristic data of the historical batch of raw milk, the purpose of which is to identify historical production scenarios with similar properties to the current raw milk; the target historical batch refers to a batch selected from the historical batches that match the current raw milk characteristics, the retention level of the specific heat-sensitive functional ingredients of its final product meets the preset target and meets other production constraints, the purpose of which is to determine a reference sample that can achieve the expected product effect; the recommended process parameters refer to a set of process parameter settings suitable for the current batch of raw milk to be produced, which are extracted or synthesized based on the selected target historical batches, the purpose of which is to provide optimized process guidance for current production.

[0018] The solution of this application builds an empirical knowledge base by recording and accumulating historical production data encompassing raw material characteristics, process parameters, and product outcomes. When a new batch of raw milk is ready for production, its characteristic data is first acquired. This data is then compared with the raw material characteristics in the historical data to identify one or more historical batches with similar characteristics. This allows the system to identify similar raw material situations encountered in past production. Next, based on preset retention targets for specific heat-sensitive functional ingredients and other production constraints (such as microbiological safety, basic physical and chemical indicators, and production efficiency), batches that have successfully achieved or nearly achieved the desired retention levels in actual production are selected. These selected batches are designated as target historical batches. Finally, process parameter data for key processes such as sterilization, concentration, and drying employed in these target historical batches is extracted and used as recommended process parameters for the current batch of raw milk. This entire process forms a closed-loop optimization and control mechanism based on historical experience, dynamically recommending validated process parameter combinations tailored to the raw material characteristics of different batches. This effectively addresses raw material fluctuations and the complex inter-process interactions, thereby improving the retention rate of specific heat-sensitive functional ingredients.

[0019] As an embodiment of the present invention, when there is no single historical batch in one or more historical batches that simultaneously meets the preset target retention level of the specific heat-sensitive functional ingredient and all other production constraints, the step of screening at least one target historical batch from the one or more historical batches based on the determined one or more historical batches and in accordance with the preset target retention level of the specific heat-sensitive functional ingredient and other production constraints includes: Setting retention level targets for specific heat-sensitive functional ingredients as a priority and establishing acceptable ranges for other production constraints; Based on the determined one or more historical batches, and according to the retention level target of the specific heat-sensitive functional ingredient corresponding to the set priority target and the acceptable range of other set production constraints, from the one or more historical batches, select historical batches whose retention level data of the specific heat-sensitive functional ingredient meets the preset retention level target and whose other production constraints are within their respective acceptable ranges as target historical batches; If multiple target historical batches meeting the conditions are obtained based on the screening, a final target historical batch is determined from the multiple target historical batches according to the preset emphasis strategy.

[0020] Among them, setting the retention level of a specific thermosensitive functional ingredient as a priority target means giving priority to whether the retention level of the ingredient meets the preset requirements when screening historical batches, with the aim of ensuring the high value-added characteristics of the final product; among them, setting an acceptance range for other production constraints means setting an acceptable fluctuation range for other production-related constraints other than the retention level of specific thermosensitive functional ingredients, rather than a strict fixed value, with the aim of increasing the number of historical batches that meet the conditions and improving data utilization; among them, the preset emphasis strategy refers to the decision rules or priority order used to determine the final recommended process parameters when there are multiple historical batches that meet the screening conditions. It can be set according to actual production needs, with the aim of selecting a solution that best meets the current production goals from multiple alternative solutions.

[0021] The solution of this application adds a flexible screening mechanism to cope with complex production constraints within the historical data similarity matching and target screening framework provided by the basic solution. After one or more historical batches that match the current raw material characteristics are determined through similarity comparison, if it is found that none of these batches can simultaneously meet the preset target retention level of the specific heat-sensitive functional ingredient and all other production constraints, this solution no longer simply discards these data. Instead, the retention level of the specific heat-sensitive functional ingredient is the primary consideration to ensure that the selected batch meets the standard on this core indicator. At the same time, recognizing that other production constraints are difficult to completely fix in practice, a reasonable acceptance range is set for these conditions. Then, a secondary screening is performed among the matching historical batches to find those batches whose retention level of the specific heat-sensitive functional ingredient meets the preset target and whose other production constraints are within their respective acceptance ranges. This approach expands the set of potential target batches and avoids the exclusion of valuable historical data due to minor deviations in individual constraints. If multiple batches that meet the conditions are still found after this flexible screening, further decision-making is required. At this point, based on a preset focus strategy, such as prioritizing cost, efficiency or other quality indicators, a final target historical batch is determined from these multiple alternative batches. The process parameters corresponding to this finalized target historical batch will be extracted as the recommended process parameters for the current batch. This method provides a pragmatic and effective data utilization strategy when perfectly matching historical data cannot be found. It can take into account other production requirements while ensuring the retention of core functional ingredients, thereby solving the problem of difficulty in effectively utilizing historical data under complex production constraints. This processing method, within the framework of historical data similarity matching and target screening provided by the basic solution, increases the ability to cope with the complexity of actual production, so that the entire self-optimization control method can still provide valuable process parameter references when faced with undesirable historical data distribution, thereby improving the robustness and practicality of the method.

[0022] As an embodiment of the present invention, the step of determining a final target historical batch from multiple target historical batches according to a preset emphasis strategy includes: Prioritizing multiple focus dimensions included in the preset focus strategy to obtain multiple focus dimensions with assigned priorities; For multiple target historical batches, and based on multiple priority-assigned focus dimensions, starting with the highest priority focus dimension, perform the following operations step by step until the final target historical batch is determined: Obtain the performance data of each target historical batch under the current processing priority dimension; Based on the acquired performance data, evaluating the performance of each target historical batch under the currently processed priority dimension to identify one or more candidate historical batches that meet predetermined criteria for the dimension; If only one candidate historical batch is identified, then the candidate historical batch becomes the final target historical batch; If multiple candidate historical batches are identified, these multiple candidate historical batches will be processed as objects of the next level of priority dimension; If after all priority dimensions are processed, the processing object obtained in the previous sub-step is still multiple candidate historical batches, then from these candidate historical batches, the historical batch with the best performance in the preset dimension related to the retention level of specific thermosensitive functional ingredients is selected as the final target historical batch.

[0023] Among them, the preset focus strategy refers to a set of pre-set rules used to guide how to select an optimal batch when there are multiple historical batches that meet the basic conditions. Specifically, it may include a series of aspects that need to be considered and their importance ranking. Its purpose is to make the final selected batch better meet specific production preferences or optimization goals; multiple focus dimensions refer to the specific considerations that constitute the preset focus strategy, such as certain specific production constraints (such as energy consumption, material loss), certain non-binding performance indicators (such as production efficiency, equipment wear), or more detailed indicators related to the retention level of specific heat-sensitive functional ingredients (such as the denaturation rate of a specific protein, the survival rate of a certain probiotic), the purpose of which is to provide a multi-angle evaluation perspective; priority assignment refers to the assignment of importance to these focus dimensions, etc. The purpose of the evaluation is to determine the order in which they are considered in the screening process, with the aim of ensuring that the most important factors are given priority in the selection process; multiple priority-assigned focus dimensions refer to a set of focus dimensions with a clear order of importance after priority assignment, with the aim of providing a basis for subsequent step-by-step screening; performance data refers to the specific numerical value or qualitative description of each target historical batch on a specific focus dimension, with the aim of providing basic information for evaluation; predetermined standards refer to the threshold or condition used to determine whether a batch meets the requirements on a certain focus dimension, such as a numerical upper or lower limit, or a range, with the aim of defining the qualified range on that dimension; candidate historical batches refer to the set of batches that are still retained and may become the final target after screening with the current priority dimension, with the aim of gradually narrowing the selection range.

[0024] The solution of the present application clarifies the factors that need to be given priority when selecting the optimal batch by assigning priorities to the multiple focus dimensions included in the preset focus strategy. Subsequently, for multiple target historical batches, based on the multiple focus dimensions with assigned priorities, starting from the focus dimension with the highest priority, the screening operation is performed step by step. In each level of screening, the performance data of each target historical batch under the dimension is first obtained, and then the performance of each batch under the dimension is evaluated based on these data, and one or more candidate historical batches that meet the predetermined standards of the dimension are identified. If there is only one candidate historical batch identified, the batch is determined as the final target historical batch, and the screening process ends. If there are multiple candidate historical batches identified, these batches are treated as the objects of the next level of priority dimension processing and continue to be screened. This step-by-step screening method ensures that the performance of the low-priority dimension is considered under the premise of meeting the requirements of the high-priority dimension, so as to systematically select batches with better overall performance from multiple qualified batches. Even if multiple candidate historical batches remain after all priority dimensions have been processed, the solution provides a fallback mechanism, selecting the historical batch with the best performance in the preset dimension related to the retention level of a specific heat-sensitive functional ingredient as the final target, further ensuring that the final batch has an advantage in achieving the core goal. Building on the above-mentioned solution's screening of multiple batches that meet the specific heat-sensitive functional ingredient retention level target and some other production constraints, this solution further provides a refined method for optimal selection based on preset preferences, enabling the entire process of process parameter recommendation to better balance multiple needs and improve the targetedness and reliability of the recommended parameters.

[0025] As an embodiment of the present invention, the step of comparing the characteristic data of the current batch of raw milk to be produced with the characteristic data of each historical batch of raw milk in the recorded historical production data for similarity includes: Classifying the current batch of raw milk to be produced into a predefined raw material state interval according to a current value of at least one preset benchmark characteristic indicator in characteristic data of the current batch of raw milk to be produced; For the classified raw material state interval, a set of weight allocation strategies that matches the currently classified raw material state interval is selected from multiple sets of preset weight allocation strategies corresponding to different raw material state intervals. The weight allocation strategy specifies the weight values of each characteristic index other than the baseline characteristic index in the raw milk characteristic data in the similarity comparison; Applying the selected weight allocation strategy, a weighted difference calculation is performed on the characteristic data of the current batch of raw milk to be produced and the corresponding characteristic indicators in the characteristic data of each historical batch of raw milk in the recorded historical production data, and the weighted differences are comprehensively calculated to complete the similarity comparison between the characteristic data of the current batch of raw milk to be produced and the characteristic data of each historical batch of raw milk in the recorded historical production data, and obtain the similarity between the current batch of raw milk to be produced and the raw milk of each historical batch.

[0026] Among them, the preset benchmark characteristic index refers to one or more indicators among the many characteristic indicators of raw milk that are predetermined to have a significant or fundamental impact on the overall state of raw milk or subsequent processing characteristics. It can be determined based on expert experience, historical data analysis or pre-set rules; the predefined raw material state interval refers to the division of the possible states of raw milk into several discrete classification intervals with specific meanings based on the numerical range of the preset benchmark characteristic index, which can be pre-defined by threshold setting based on the benchmark characteristic index, cluster analysis or manual experience division; the preset multiple sets of weight allocation strategies corresponding to different raw material state intervals refer to a set of specific rules for the importance weights of each characteristic indicator in the similarity comparison configured in advance for each predefined raw material state interval, which can be pre-configured and corresponded based on experimental data, expert knowledge or machine learning model training results on the degree of influence of each characteristic indicator under different raw material states on the retention level of specific heat-sensitive functional ingredients; the weight allocation strategy stipulates the characteristics of other characteristics in the raw milk characteristic data except the benchmark characteristic indicators. The weight value of an indicator in a similarity comparison refers to a numerical value assigned to each characteristic indicator involved in the comparison, except for the benchmark characteristic indicator used to classify the raw material status. This numerical value reflects the relative importance of the characteristic indicator in evaluating the similarity of raw milk in this specific raw material status range; weighted difference calculation refers to calculating the numerical difference between each characteristic indicator other than the benchmark characteristic indicator when comparing the characteristic data of the current batch of raw milk to be produced with the historical batch of raw milk, and multiplying the difference by the weight value corresponding to the characteristic indicator under the currently selected weight allocation strategy. It can be calculated by multiplying the absolute difference by the weight, multiplying the square difference by the weight, etc.; comprehensive weighted difference refers to summing up the weighted difference values of all characteristic indicators involved in the weighted difference calculation to obtain a single numerical value. This numerical value reflects the overall similarity or difference between the current batch of raw milk to be produced and a historical batch of raw milk after taking into account the difference in importance of each characteristic indicator. It can be synthesized by summing up the weighted difference values, weighted averaging, or constructing a distance metric based on the weighted difference.

[0027] The solution of the present application categorizes the current batch of raw milk to be produced into a predefined raw material state interval based on the current value of at least one preset baseline characteristic indicator of the current batch of raw milk to be produced, thereby classifying raw milk with similar characteristics into the same interval, laying the foundation for the subsequent use of different weight allocation strategies, because the characteristic indicators of raw milk in different states may have different degrees of influence on the final product. On this basis, for the classified raw material state interval, a set of weight allocation strategies that matches the current classified raw material state interval is selected from multiple sets of preset weight allocation strategies corresponding to different raw material state intervals. The weight allocation strategy specifies the weight values of each characteristic indicator in the raw milk characteristic data other than the baseline characteristic indicator in the similarity comparison. By configuring different weight allocation strategies for different raw material state intervals, the importance of each characteristic indicator in the similarity comparison can be more flexibly adjusted, thereby more accurately reflecting the degree of influence of different characteristic indicators on the final product and avoiding the deviation that may be caused by the use of a unified weight. Subsequently, the selected weight distribution strategy is applied to calculate the weighted difference between the characteristic data of the current batch of raw milk to be produced and the corresponding characteristic indicators in the characteristic data of each historical batch of raw milk in the recorded historical production data. The weighted differences are then combined to complete the similarity comparison between the characteristic data of the current batch of raw milk to be produced and the characteristic data of each historical batch of raw milk in the recorded historical production data, thereby obtaining the similarity between the current batch of raw milk to be produced and the raw milk of each historical batch. Through the weighted difference calculation, the influence of important characteristic indicators can be highlighted and the influence of unimportant characteristic indicators can be weakened, thereby more accurately assessing the similarity between the current batch of raw milk to be produced and the raw milk of historical batches. This method of dynamically adjusting the comparison focus based on the characteristics of the raw materials themselves makes the similarity comparison results more reflective of the potential behavior of raw milk in actual production, thereby providing more accurate input for subsequent process parameter recommendations and significantly improving the effectiveness of the recommended parameters in achieving the retention target of specific heat-sensitive functional ingredients.

[0028] As an embodiment of the present invention, when there are multiple target historical batches screened out, the step of extracting process parameter data covering key processes of goat milk powder production corresponding to at least one of the screened out target historical batches as recommended process parameters for the current batch of raw milk to be produced includes: Gather the parameter values of various process parameters for each key process of goat milk powder production from multiple target historical batches; Obtaining data on the retention levels of specific heat-sensitive functional ingredients in the final product for each of multiple target historical batches; identifying, based on the aggregated parameter values of the various process parameters, a process parameter having a predetermined degree of influence on the retention level of a specific heat-sensitive functional ingredient among the various process parameters; For the identified process parameter with a preset impact, a single parameter value of the process parameter is determined based on the obtained retention level data of multiple target historical batches and the parameter values of the process parameter corresponding to these historical batches; For a process parameter that is not identified as having a preset impact level, determining a single parameter value of the process parameter based on parameter values of the process parameter corresponding to multiple target historical batches; The single parameter values determined for various process parameters are combined to form a set of single recommended process parameters covering the key processes of goat milk powder production, which serve as the recommended process parameters for the current batch of raw milk to be produced.

[0029] The process parameters for key goat milk powder production processes refer to specific set values or measured values, such as temperature, time, pressure, flow rate, and concentration, used to control equipment operating conditions and material handling conditions during various operational steps (e.g., sterilization, concentration, and drying) that significantly impact product quality, particularly the retention level of specific heat-sensitive functional ingredients. Retention level data for specific heat-sensitive functional ingredients refers to quantitative data on the content, activity, or relative initial content of one or more heat-sensitive ingredients with specific biological activity (e.g., active proteins, probiotics) in the final goat milk powder product. Identifying process parameters with a predetermined degree of influence on the retention level of specific heat-sensitive functional ingredients involves determining, through analysis of historical data or based on prior knowledge, which process parameters show a significant correlation or causal relationship, reaching a predetermined threshold, with the retention level of specific heat-sensitive functional ingredients in the final product. This can be achieved using statistical analysis methods, machine learning models, or expert system rules. A preset level of influence refers to a pre-set quantitative standard or threshold used to distinguish between parameters with significant impact (with a preset level of influence) and those with insignificant impact when identifying the impact of a process parameter on the retention level of a specific heat-sensitive functional ingredient. This standard can be set based on statistical significance, impact size, or business importance. Determining a single parameter value for a process parameter means, for a specific process parameter, using a calculation or decision-making method to derive a single parameter setting value that is ultimately recommended for the current production batch from the parameter values corresponding to multiple target historical batches. For parameters with a preset level of influence, the determination method will consider their relationship to the retention level; for parameters without a preset level of influence, the determination method may focus more on the central trend of the parameter values.

[0030] The proposed solution aggregates process parameter values and corresponding retention data for specific heat-sensitive functional ingredients from multiple target historical batches, providing a comprehensive data foundation for subsequent analysis. Based on this data, the solution further identifies key process parameters with a predetermined impact on the retention level of the specific heat-sensitive functional ingredient. This distinction between key and non-critical parameters allows the solution to employ different strategies for different parameter types. For key parameters with significant impact, a comprehensive analysis based on retention data and parameter values from historical batches is conducted to determine a single parameter value that is more conducive to high retention levels. For non-critical parameters with less significant impact, a relatively simple approach can be used to determine a single parameter value. This divide-and-conquer, prioritized strategy more effectively leverages the complex relationships between parameters and effects revealed in the historical data. It specifically optimizes those parameters with the greatest impact on the target effect (retention of the specific heat-sensitive functional ingredient), thereby generating a set of recommended parameters with a greater likelihood of achieving high retention levels. This approach, combined with the prior approach to identify multiple batches that meet the predetermined retention target, fully utilizes the information from these excellent batches, rather than wasting the majority of the data. This overcomes the potential for randomness and suboptimality associated with simplistic selection, improving the reliability and optimization of the recommended parameters. Finally, the single parameter values determined for each process parameter will be combined to form a single set of recommended process parameters covering the key processes of goat milk powder production, which can be directly applied to the processing of raw milk of the current batch to be produced, thereby optimizing the production process in a more targeted manner and improving the retention level of specific heat-sensitive functional ingredients.

[0031] As an embodiment of the present invention, for an identified process parameter having a preset impact, the step of determining a single parameter value of the process parameter based on the obtained retention level data of multiple target historical batches and the parameter values of the process parameter corresponding to these historical batches includes: From a plurality of target historical batches that meet the criteria, screening out one or more target historical batches that meet the criteria, based on the retention level data of the specific heat-sensitive functional ingredient in the final product of each target historical batch; If only one target historical batch that meets the criteria is screened out, the parameter value of the process parameter with the preset degree of influence corresponding to the target historical batch that meets the criteria is adopted as a single parameter value of the process parameter with the preset degree of influence; If there are multiple target historical batches that meet the criteria, a single parameter value of the process parameter with a preset degree of influence is determined through a preset parameter processing rule based on the set of parameter values of the process parameters with a preset degree of influence corresponding to the multiple target historical batches that meet the criteria.

[0032] Among them, the preset standard refers to the threshold or range used to measure whether the retention level of a specific thermosensitive functional ingredient meets the expected requirements. It can be expressed as a specific percentage value, a numerical range or a grade rating. Its purpose is to identify those historical batches that perform well in the retention of specific functional ingredients; the preset parameter processing rule refers to the calculation method or logic used to integrate multiple parameter values to determine a single representative value. It can be achieved by average calculation, weighted average calculation, median selection or prediction based on statistical models. Its purpose is to extract a representative parameter value that helps to optimize the retention level from the data of multiple excellent historical batches.

[0033] The solution of the present application determines the single parameter value of the process parameter with a preset degree of influence identified based on the retention level data and corresponding parameter values of multiple target historical batches. First, from multiple target historical batches that meet the standards, one or more target historical batches that meet the standards are screened out based on the retention level data of specific heat-sensitive functional ingredients in the final products of each batch. This screening process focuses on batches that perform well in retaining the target ingredients, which is equivalent to a quality filtering of the original data, eliminating the interference of batch data with lower retention levels on parameter determination. Then, branch processing is performed based on the screening results: if there is only one target historical batch that meets the standards, the parameter value of the process parameter with a preset degree of influence corresponding to the batch is directly adopted as the single parameter value, which ensures that when there is a clear optimal historical batch, its successful experience can be directly adopted; if there are multiple target historical batches that meet the standards, the single parameter value is determined based on the parameter value set of the process parameter with a preset degree of influence corresponding to these excellent batches through the preset parameter processing rules. This approach integrates parameter information from multiple excellent batches and balances data from different batches through specific algorithms or logic, resulting in a more robust and representative recommended parameter value, avoiding the accidental bias that may arise from relying solely on data from a single batch. This process refines and optimizes the steps in the basic solution that simply aggregate parameter values, identify influencing parameters, and then determine a single parameter value. This allows the values of key influencing parameters to be more accurately anchored to historical data that has been proven to achieve high retention levels in actual production, thereby improving the effectiveness of the final recommended process parameters and helping to better achieve the goal of maximizing the retention of specific heat-sensitive functional ingredients in actual production.

[0034] As an embodiment of the present invention, the step of determining a single parameter value of a process parameter having a preset influence degree by using a preset parameter processing rule includes: Based on the retention level data of the specific heat-sensitive functional ingredient in the final products of multiple target historical batches that meet the standards, the parameter values of the process parameters with the preset impact level are weighted averaged to obtain a single parameter value of the process parameter with the preset impact level.

[0035] The term "multiple target historical batches meeting the criteria" refers to a collection of historical production batches whose retention data for specific heat-sensitive functional ingredients in the final product meet preset criteria after preliminary and further screening. The retention data for specific heat-sensitive functional ingredients in the final product refers to a quantitative value reflecting the degree of retention of the specific heat-sensitive functional ingredient, obtained through testing and analysis of each batch of final goat milk powder produced during the historical production process. This value can be expressed as a percentage, content per unit mass, or relative activity. A process parameter with a preset degree of influence refers to a process control variable in a key step in goat milk powder production that, after analysis and identification, has been determined to have a significant or important impact on the retention level of the specific heat-sensitive functional ingredient in the final product. A parameter value refers to the specific numerical setting or measurement actually used or recorded for a process parameter with a preset degree of influence during the production of a specific historical batch. Weighted average refers to a statistical averaging method that calculates the average based on the contribution of each data point to the final result. This can be achieved using different weighting calculation and application methods. A single parameter value is a unique recommended setting value obtained by weighted average calculation to represent a process parameter with a preset degree of influence.

[0036] The solution of the present application obtains a single parameter value for a process parameter with a preset degree of influence by weighted averaging the parameter values of process parameters with a preset degree of influence based on the retention level data of a specific heat-sensitive functional ingredient in the final product of each of multiple target historical batches that meet the standards. Specifically, after identifying the process parameters with a preset degree of influence on the retention level of the specific heat-sensitive functional ingredient, and after screening multiple target historical batches whose retention levels meet the preset standards, this solution uses the retention level data corresponding to these batches as weight information. The higher the retention level, the more favorable the process parameter value corresponding to the batch is for achieving a high retention level, and therefore it is assigned a higher weight in the weighted average. In this way, the final calculated single parameter value will tend to favor those parameter settings that have been proven to produce higher retention levels in historical practice. This method, combined with the aforementioned data recording, preliminary matching screening, key parameter identification, and high retention level batch screening, forms a complete self-optimizing control process. It provides a method for finely integrating the parameter values of multiple high retention level batches based on the screening of multiple high retention level batches. Rather than simply selecting or averaging, it weights results based on actual retention, leveraging historical data to better leverage the best-performing experiences. This allows the final recommended process parameters to more accurately reflect their association with high retention levels, thus better guiding parameter settings in actual production and improving the retention of specific heat-sensitive functional ingredients. This weighted averaging based on performance feedback enables the system to learn from historical experience and optimize parameter settings, addressing raw material fluctuations and inter-process impacts, and achieving continuous improvement towards specific goals.

[0037] As an embodiment of the present invention, the step of performing weighted averaging on parameter values of process parameters with preset influence degrees includes: normalizing the retention level data of the specific heat-sensitive functional ingredient based on the retention level data of the specific heat-sensitive functional ingredient in the final products of each of a plurality of target historical batches that meet the criteria; The normalized retention level data is used as a weight to perform weighted averaging on the parameter values of the process parameters with a preset degree of influence, thereby obtaining a single parameter value of the process parameter with a preset degree of influence.

[0038] Among them, normalization processing refers to converting data of different dimensions or numerical ranges to a unified scale. It can be achieved by using methods such as minimum-maximum normalization and Z-score normalization. Its purpose is to eliminate the dimensional influence between data and make them comparable; among them, weighted average refers to assigning different weights to different data points when calculating the average value. The weight reflects the importance of the data point in the calculation. Its purpose is to make important data points have a greater impact on the results.

[0039] The solution of the present application is to normalize the retention level data of the specific heat-sensitive functional ingredient according to the retention level data of the specific heat-sensitive functional ingredient in the final product of each of the target historical batches that meet the standards, thereby unifying the retention level data of different historical batches into a comparable range, eliminating the impact caused by the difference in the dimension or numerical range of the original data, and making the subsequent weighted average more reasonable and effective. Then, the normalized retention level data is used as a weight to perform a weighted average on the parameter values of the process parameters with a preset degree of influence to obtain a single parameter value of the process parameter with a preset degree of influence. This means that the higher the retention level of the historical batch, the greater the proportion of its corresponding process parameter value in the final determined single parameter value. This processing method is combined with the overall framework of determining recommended parameters from multiple target historical batches. In particular, after screening out multiple historical batches that meet specific retention level standards, this solution can make more detailed use of the data of these batches. By normalizing the retention level data and using it as a weight, we can make more effective use of the experience of historical batches that perform better in retaining specific heat-sensitive functional ingredients, thereby making it more likely to obtain a process parameter value that can better retain the specific functional ingredient, overcoming the shortcoming of simple averaging that may ignore differences in retention levels.

[0040] As an embodiment of the present invention, the steps of using the normalized retention level data as a weight to perform weighted averaging on the parameter values of the process parameters with a preset influence degree to obtain a single parameter value of the process parameter with a preset influence degree include: Calculate the product of the weight value of each batch and the parameter value to obtain the weighted parameter value; Sum all weighted parameter values to obtain the weighted sum; Sum all weight values to get the total weight; Divide the weighted sum by the sum of the weights to get a single parameter value.

[0041] Among them, the retention level data of specific heat-sensitive functional ingredients in the final products of multiple target historical batches that meet the standards are normalized, which can convert these data to a unified scale, thereby ensuring the comparability of data between different batches. Using the normalized retention level data as a weight means that the higher the retention level of the batch, the greater the contribution of its corresponding process parameters to the final recommended value. Calculating the product of the weight value and the parameter value of each batch to obtain a weighted parameter value is to combine the information of each batch on the retention level and process parameters. Summing all weighted parameter values to obtain a weighted sum is the weighted contribution of all target historical batches. Summing all weight values to obtain the weighted sum is the weighted weight of all batches. Dividing the weighted sum by the weighted sum to obtain a single parameter value is a standard method for performing a weighted average calculation, thereby determining a recommended parameter value that comprehensively considers the experience of multiple high retention level batches.

[0042] Specifically, after identifying multiple target historical batches that meet the retention target for a specific heat-sensitive functional ingredient and other production constraints, a single recommended parameter value is determined from the process parameters corresponding to these batches. To ensure that the determined parameter value better reflects the experience of batches with high retention levels, a weighted average approach is employed. First, the retention level data for the specific heat-sensitive functional ingredient in the final product of each target historical batch is normalized. This converts the retention level data from different batches to a unified scale, ensuring data comparability and providing a reliable basis for subsequent weighted calculations. The normalized retention level data is used as the weight. Higher retention levels correspond to larger normalized weights, indicating that the process parameters for that batch have greater reference value in achieving high retention levels. The weight value for each batch is multiplied by the parameter value of its corresponding process parameter with a preset impact level to obtain the weighted parameter value for that batch. The weighted parameter values for all batches are then accumulated to obtain the weighted sum. The weighted sum is then calculated by summing the weighted values for all batches. A single parameter value of the process parameter with a preset degree of influence is calculated by dividing the weighted sum by the weight sum.

[0043] like Figure 2 A self-optimizing and controlling system for process parameters of goat milk powder production is shown, and the system comprises: Data recording module 201 is used to record historical production data, including raw milk property data of historical batches, process parameter data covering key production processes of goat milk powder based on the raw milk property data of historical batches, and retention level data of specific heat-sensitive functional ingredients in the final product produced using the process parameter data. The key production processes of goat milk powder include at least sterilization, concentration, and drying. Current data acquisition module 202, used to obtain characteristic data of the current batch of raw milk to be produced; A similarity comparison module 203 is configured to perform a similarity comparison between the acquired characteristic data of the current batch of raw milk to be produced and the characteristic data of each historical batch of raw milk in the recorded historical production data, so as to determine one or more historical batches whose characteristics match those of the current batch of raw milk to be produced; a target batch screening module 204 for screening at least one target historical batch from the one or more historical batches based on the determined one or more historical batches and according to a preset retention level target for the specific heat-sensitive functional ingredient and other production constraints, wherein the retention level data of the specific heat-sensitive functional ingredient in the final product of the target historical batch meets the preset retention level target; The parameter extraction module 205 is used to extract the process parameter data covering the key processes of goat milk powder production corresponding to the at least one selected target historical batch as the recommended process parameters for the current batch of raw milk to be produced.

[0044] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. Various changes and improvements are possible without departing from the spirit and scope of the present invention, and such changes and improvements fall within the scope of the invention as claimed.

Claims

1. A method for self-optimization and control of process parameters for goat milk powder production, applied to a goat milk powder production process with the goal of maximizing the retention of specific heat-sensitive functional ingredients, characterized in that: The method comprises the following steps: Recording historical production data, including raw milk property data of historical batches, process parameter data covering key steps in goat milk powder production based on the raw milk property data of the historical batches, and retention level data of specific heat-sensitive functional ingredients in the final product produced using the process parameter data; Obtain characteristic data of the current batch of raw milk to be produced; Based on the acquired characteristic data of the current batch of raw milk to be produced, performing a similarity comparison between the characteristic data of the current batch of raw milk to be produced and the characteristic data of raw milk of each historical batch in the recorded historical production data, to determine one or more historical batches whose characteristics match the characteristics of the current batch of raw milk to be produced; Based on the determined one or more historical batches and according to a preset retention level target for the specific heat-sensitive functional ingredient and other production constraints, at least one target historical batch is selected from the one or more historical batches, wherein the retention level data of the specific heat-sensitive functional ingredient in the final product of the target historical batch meets the preset retention level target; The process parameter data covering the key processes of goat milk powder production corresponding to at least one selected target historical batch is extracted as the recommended process parameters for the current batch of raw milk to be produced.

2. A method for self-optimizing and controlling process parameters for producing goat milk powder according to claim 1, characterized in that: When there is no single historical batch that satisfies both the preset target retention level of the specific heat-sensitive functional ingredient and all other production constraints among the one or more historical batches, the step of selecting at least one target historical batch from the one or more historical batches based on the determined one or more historical batches and in accordance with the preset target retention level of the specific heat-sensitive functional ingredient and other production constraints includes: setting a target retention level of the specific heat-sensitive functional ingredient as a priority target and setting an acceptable range for the other production constraints; Based on the determined one or more historical batches, and according to the set retention level target of the specific heat-sensitive functional ingredient corresponding to the priority target and the set acceptable range of the other production constraints, from the one or more historical batches, historical batches whose retention level data of the specific heat-sensitive functional ingredient meets the preset retention level target and whose other production constraints are all within the respective acceptable ranges are screened as target historical batches; If multiple target historical batches meeting the conditions are obtained based on the screening, a final target historical batch is determined from the multiple target historical batches according to a preset emphasis strategy.

3. A method for self-optimizing and controlling process parameters for producing goat milk powder according to claim 2, characterized in that: The step of determining a final target historical batch from multiple target historical batches according to a preset emphasis strategy includes: Prioritizing the multiple emphasis dimensions included in the preset emphasis strategy to obtain multiple emphasis dimensions with assigned priorities; For multiple target historical batches, and based on the multiple priority-based dimensions, starting with the highest priority dimension, the following operations are performed step by step until a final target historical batch is determined: Obtain the performance data of each target historical batch under the current processing priority dimension; Based on the obtained performance data, evaluating the performance of each target historical batch under the priority dimension currently being processed to identify one or more candidate historical batches that meet predetermined criteria for the dimension; If only one candidate historical batch is identified, then the candidate historical batch becomes the final target historical batch; If multiple candidate historical batches are identified, these multiple candidate historical batches will be processed as objects of the next level of priority dimension; If after all priority dimensions are processed, the processing object obtained in the previous sub-step is still multiple candidate historical batches, then from these candidate historical batches, the historical batch with the best performance in the preset dimension related to the retention level of the specific thermosensitive functional ingredient is selected as the final target historical batch.

4. A method for self-optimizing and controlling process parameters for producing goat milk powder according to claim 1, characterized in that: The step of performing similarity comparison between the characteristic data of the current batch of raw milk to be produced and the characteristic data of each historical batch of raw milk in the recorded historical production data comprises: Classifying the current batch of raw milk to be produced into a predefined raw material state interval according to a current value of at least one preset benchmark characteristic indicator in the characteristic data of the current batch of raw milk to be produced; For the classified raw material state interval, a set of weight allocation strategies that matches the currently classified raw material state interval is selected from multiple sets of preset weight allocation strategies corresponding to different raw material state intervals, wherein the weight allocation strategy specifies the weight values of each characteristic index other than the baseline characteristic index in the raw milk characteristic data in the similarity comparison; Applying the selected weight allocation strategy, a weighted difference calculation is performed on the characteristic data of the current batch of raw milk to be produced and the corresponding characteristic indicators in the characteristic data of each historical batch of raw milk in the recorded historical production data, and the weighted differences are integrated to complete the similarity comparison between the characteristic data of the current batch of raw milk to be produced and the characteristic data of each historical batch of raw milk in the recorded historical production data, so as to obtain the similarity between the current batch of raw milk to be produced and the raw milk of each historical batch.

5. A method for self-optimizing and controlling process parameters for goat milk powder production according to claim 1, characterized in that: When there are multiple target historical batches screened out, the step of extracting process parameter data covering key processes of goat milk powder production corresponding to at least one of the screened out target historical batches as recommended process parameters for the current batch of raw milk to be produced includes: Gather the parameter values of various process parameters for each key process of goat milk powder production from multiple target historical batches; Obtaining data on the retention levels of specific heat-sensitive functional ingredients in the final product for each of multiple target historical batches; Based on the collected parameter values of the various process parameters, identifying a process parameter among the various process parameters that has a predetermined degree of influence on the retention level of the specific heat-sensitive functional ingredient; For the identified process parameter with a preset impact, determining a single parameter value of the process parameter based on the obtained retention level data of multiple target historical batches and the parameter values of the process parameter corresponding to these historical batches; For a process parameter that is not identified as having a preset impact level, determining a single parameter value of the process parameter based on parameter values of the process parameter corresponding to multiple target historical batches; The single parameter values determined for the various process parameters are combined to form a set of single recommended process parameters covering the key processes of goat milk powder production, which are used as recommended process parameters for the current batch of raw milk to be produced.

6. A method for self-optimizing and controlling process parameters for goat milk powder production according to claim 5, characterized in that: The step of determining a single parameter value of the process parameter identified as having a preset impact based on the obtained retention level data of multiple target historical batches and the parameter values of the process parameter corresponding to these historical batches includes: From a plurality of target historical batches that meet the criteria, screening out one or more target historical batches that meet the criteria, based on the retention level data of the specific heat-sensitive functional ingredient in the final product of each target historical batch; If only one target historical batch that meets the criteria is screened out, the parameter value of the process parameter with the preset degree of influence corresponding to the target historical batch that meets the criteria is adopted as a single parameter value of the process parameter with the preset degree of influence; If there are multiple target historical batches that meet the criteria, a single parameter value of the process parameter with a preset degree of influence is determined through a preset parameter processing rule based on the set of parameter values of the process parameters with a preset degree of influence corresponding to the multiple target historical batches that meet the criteria.

7. A method for self-optimizing and controlling process parameters for goat milk powder production according to claim 6, characterized in that: The step of determining a single parameter value of a process parameter with a preset influence degree by using a preset parameter processing rule includes: Based on the retention level data of specific heat-sensitive functional ingredients in the final products of multiple target historical batches that meet the standards, the parameter values of the process parameters with a preset impact degree are weighted averaged to obtain a single parameter value of the process parameter with the preset impact degree.

8. A method for self-optimizing and controlling process parameters for goat milk powder production according to claim 7, characterized in that: The step of performing weighted averaging on the parameter values of the process parameters with a preset influence degree comprises: normalizing the retention level data of the specific heat-sensitive functional ingredient according to the retention level data of the specific heat-sensitive functional ingredient in the final products of each of the plurality of target historical batches that meet the criteria; The normalized retention level data is used as a weight to perform weighted averaging on the parameter values of the process parameters with a preset degree of influence, thereby obtaining a single parameter value of the process parameter with a preset degree of influence.

9. A method for self-optimizing and controlling process parameters for goat milk powder production according to claim 8, characterized in that: The steps of taking the normalized retention level data as weights and performing weighted averaging on the parameter values of the process parameters with a preset influence degree to obtain a single parameter value of the process parameter with a preset influence degree include: Calculate the product of the weight value of each batch and the parameter value to obtain the weighted parameter value; Sum all weighted parameter values to obtain the weighted sum; Sum all weight values to get the total weight; The weighted sum is divided by the weight sum to obtain the single parameter value.

10. A goat milk powder production process parameter self-optimization control system, characterized in that: The system includes: A data recording module for recording historical production data, the historical production data including raw milk property data of historical batches, process parameter data covering key steps in goat milk powder production based on the raw milk property data of the historical batches, and retention level data of specific heat-sensitive functional ingredients in the final product produced using the process parameter data; The current data acquisition module is used to obtain the characteristic data of the current batch of raw milk to be produced; a similarity comparison module for performing a similarity comparison between the acquired characteristic data of the current batch of raw milk to be produced and the characteristic data of each historical batch of raw milk in the recorded historical production data, so as to determine one or more historical batches whose characteristics match those of the current batch of raw milk to be produced; a target batch screening module, configured to screen at least one target historical batch from the one or more historical batches based on the determined one or more historical batches and according to a preset retention level target for the specific heat-sensitive functional ingredient and other production constraints, wherein the retention level data of the specific heat-sensitive functional ingredient in the final product of the target historical batch meets the preset retention level target; The parameter extraction module is used to extract the process parameter data covering the key processes of goat milk powder production corresponding to at least one selected target historical batch as the recommended process parameters for the current batch of raw milk to be produced.

Images