An intelligent control system for the freeze-drying process of probiotic seaweed

Abstract

The present invention discloses an intelligent control system for the freeze-drying process of probiotic seaweed, which relates to the field of freeze-drying technology. The preliminary experimental module establishes a detailed experimental database by real-time monitoring of the number of surviving probiotics in the seaweed to be dried, providing reliable data support for subsequent analysis. The screening module effectively identifies the drying conditions that have a significant impact on the activity of probiotics by calculating the influence coefficient Yxxs, ensuring that the activity of probiotics during the drying process is retained as much as possible. The combination analysis module generates a variety of drying condition combinations through a combinatorial method, flexibly explores relatively optimal drying schemes, thereby improving drying efficiency and product consistency. The post-drying analysis module uses convolutional neural network technology to calculate the brittleness index Chzs based on the monitored quality data, and fits the balance evaluation index Pgzs, providing a scientific basis for evaluating product quality.

Description

Technical Field

[0001] The invention relates to the technical field of freeze drying, and in particular to an intelligent control system for a probiotic seaweed freeze drying process. Background Art

[0002] With the continuous development of food science and technology, the study of probiotics has gradually become an important part of the field of functional foods, which aims to improve the nutritional value and health functions of food by adding microorganisms that are beneficial to human health. As an emerging health food, probiotic seaweed combines the nutritional properties of seaweed and the health benefits of probiotics, and is favored by more and more consumers. In this context, freeze-drying, as an efficient preservation technology, is particularly important in retaining the activity of probiotics and the flavor of seaweed. Therefore, in-depth analysis of the freeze-drying process of probiotic seaweed and the development of an intelligent control system have become the key to promoting the development of this field.

[0003] In the freeze-drying process of probiotic seaweed, traditional methods often face many challenges, resulting in loss of probiotic activity and unstable product quality. The existing technology lacks systematicity in the selection and monitoring of drying conditions, making it difficult to achieve real-time feedback and adjustment, resulting in the loss of crispness and nutritional value of the finished product. In addition, the lack of in-depth analysis of the impact of different drying conditions on the survival rate of probiotics makes it difficult to determine the optimal range of drying parameters. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent control system for the freeze-drying process of probiotic seaweed, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent control system for the freeze-drying process of probiotic seaweed, including a preliminary experiment module, a screening module, a combination analysis module, a post-drying analysis module and a feedback module;

[0006] The preliminary experiment module is used to detect the number of surviving probiotics in the dried seaweed through the culture medium, and control different drying conditions to monitor the number of surviving probiotics in the dried seaweed in real time to build an experimental database;

[0007] The screening module is used to analyze the effects of different drying conditions on the activity of probiotics according to the experimental database to calculate the influence coefficient Yxxs, and preliminarily screen out the drying conditions that have an impact on the probiotics based on the numerical value of the influence coefficient Yxxs, and compare the number of probiotic survivals corresponding to the screened drying conditions with the preset activity requirements to screen out the range value of each single drying condition again;

[0008] The combination analysis module is used to filter out the range values ​​of each single drying condition in the screening module, generate a plurality of combined drying conditions through the combination operation in combinatorial science, and randomly extract a combined drying condition from the plurality of combined drying conditions to calculate and obtain the setting index Sdzs between the corresponding combined items;

[0009] The post-drying analysis module is used to monitor the relevant quality data information of the seaweed after freeze-drying, and analyze and calculate the brittleness index Chzs according to the relevant quality data information, and input the brittleness index Chzs and the set index Sdzs into the comprehensive quality prediction model constructed by using the convolutional neural network technology to fit the balance evaluation index Pgzs;

[0010] The feedback module is used to pre-set the evaluation threshold W, and compare and analyze it with the balance evaluation index Pgzs to comprehensively judge the qualified status of the current seaweed after freeze-drying, and take corresponding optimization measures according to the qualified status.

[0011] Preferably, the preliminary experiment module includes a pre-drying unit and a condition testing unit;

[0012] The pre-drying unit is used to pre-coat the outer surface of the seaweed to be dried with a protective agent, wherein the protective agent includes glycerol and glucose, and at the same time, the number of viable probiotics in the seaweed to be dried is detected by a culture medium, and the active probiotics are stained by an active staining method, and then the proportion of active probiotics is monitored by a flow cytometer;

[0013] The condition testing unit is used to monitor the survival number of probiotics in the dried seaweed while controlling different drying conditions, and to match the survival number corresponding to each drying condition to construct an experimental database.

[0014] Preferably, the screening module includes a single drying condition difference analysis unit, an impact unit, a preliminary screening unit and a range screening unit;

[0015] The single drying condition difference analysis unit is used to set different values ​​of the single parameter, and monitor the survival number of probiotics at each monitoring time point under different values, so as to analyze the difference of the single parameter under the drying conditions with different values, and respectively calculate and obtain the inter-group difference value Zfc and the intra-group difference value Znc, which are specifically obtained in the following manner:

[0016] ;

[0017] In the formula, n represents the number of groups of values ​​set for a single parameter, i=1, 2, 3, ..., n, is represented by the number of samples in the i-th group, It is expressed as the mean number of surviving probiotics in group i, It is expressed as the mean of the number of surviving probiotics in all groups in a single parameter;

[0018] ;

[0019] Where j = 1, 2, 3, ..., , It is expressed as the number of surviving probiotics at the jth monitoring time point in the i-th group.

[0020] Preferably, the influencing unit is used to analyze the influence of different drying conditions on the activity of probiotics according to the experimental database and based on the inter-group difference value Zfc and the intra-group difference value Znc, so as to calculate the influence coefficient Yxxs, which is specifically obtained by the following method:

[0021] ;

[0022] In the formula, n represents the number of groups of values ​​set for a single parameter; N represents the number of samples in all groups of a single parameter;

[0023] The preliminary screening unit is used to pre-set a safety threshold, and compare and analyze the influence coefficient Yxxs with the safety threshold to preliminarily screen out the drying conditions that affect the probiotics. The specific contents are as follows:

[0024] If the influence coefficient Yxxs exceeds the safety threshold, it is preliminarily judged that the current single parameter has an impact on the probiotics, and a range reduction instruction will be issued at this time;

[0025] If the impact coefficient Yxxs does not exceed the safety threshold, it is preliminarily judged that the current single parameter has no impact on the probiotics.

[0026] Preferably, the range screening unit is used to compare the number of probiotic survivals corresponding to the screened drying conditions with the preset activity requirements after receiving the range reduction instruction, so as to screen out the range value of each single drying condition again, specifically:

[0027] If the number of surviving probiotics corresponding to the screened drying conditions exceeds the preset activity requirement, the corresponding drying conditions are included in the range value of the corresponding single parameter;

[0028] If the number of surviving probiotics corresponding to the screened drying conditions does not exceed the preset activity requirement, the corresponding drying conditions will not be included in the range value of the corresponding single parameter.

[0029] Preferably, the combination analysis module is used to extract a combination item drying condition from a plurality of combination item drying conditions, and after dimensionless processing, calculate and obtain the setting index Sdzs between the corresponding combination items, which is specifically obtained in the following manner:

[0030] ;

[0031] In the formula, Represented as the weight value of the kth single parameter, It represents the specific regulation value of the kth single parameter, K represents the number of single parameters, k=1, 2, 3, ..., K.

[0032] Preferably, the post-drying analysis module includes a quality monitoring unit, a quality analysis unit and a comprehensive evaluation unit;

[0033] The quality monitoring unit is used to monitor the relevant quality data information of the seaweed after freeze-drying the seaweed to be dried using several groups of monitoring equipment, wherein the relevant quality data information includes vacuum degree Zkd, drying time Gsc and moisture content Shz.

[0034] Preferably, the mass analysis unit is used to process the vacuum degree Zkd, drying time Gsc and moisture content Shz dimensionlessly according to the relevant quality data information, and map the corresponding data values ​​to the interval The embrittlement index Chzs is calculated by analysis, and the embrittlement index Chzs is obtained by the following method:

[0035] ;

[0036] In the formula, and are all weight values, and C represents the first correction constant.

[0037] Preferably, the comprehensive evaluation unit is used to construct a comprehensive quality prediction model by using convolutional neural network technology, and input the embrittlement index Chzs and the set index Sdzs into the comprehensive quality prediction model, and after dimensionless processing, fit the balance evaluation index Pgzs, which is specifically obtained in the following manner:

[0038] ;

[0039] In the formula, and are all weight values, and G represents the second correction constant.

[0040] Preferably, the feedback module includes a comparison unit and an optimization feedback unit;

[0041] The comparison unit is used to compare and analyze the evaluation threshold W with the balance evaluation index Pgzs to comprehensively judge the qualified status of the current seaweed after freeze-drying. The specific comparison content is as follows:

[0042] If the balance evaluation index Pgzs does not exceed the evaluation threshold W, it is comprehensively judged that the current freeze-dried seaweed is not in a qualified state;

[0043] If the balance evaluation index Pgzs exceeds the evaluation threshold W, it is comprehensively judged that the current freeze-dried seaweed is in a qualified state;

[0044] The optimization feedback unit is used to take corresponding optimization measures according to the comparison results in the comparison unit, and the specific contents are as follows:

[0045] If it is not in qualified condition, the value of each single parameter will be readjusted to prevent embrittlement and protect the activity of probiotics. At the same time, the air flow distribution during the freeze-drying process will be adjusted, and an alarm mechanism will be set. When unqualified conditions are detected, it will be automatically recorded and the operator will be prompted.

[0046] If it is in qualified condition, the current drying conditions will continue to be used, the quality of the seaweed and the activity of probiotics will be tested regularly, and the successful drying parameter settings will be recorded.

[0047] The present invention provides an intelligent control system for the freeze-drying process of probiotic seaweed, which has the following beneficial effects:

[0048] (1) The system further improves the efficiency of the freeze-drying process and product quality through the collaborative work of multiple modules. First, the preliminary experiment module establishes a detailed experimental database by real-time monitoring the number of probiotics surviving in the dried seaweed, providing reliable data support for subsequent analysis. The screening module effectively identifies the drying conditions that have a significant impact on the activity of probiotics by calculating the influence coefficient Yxxs, ensuring that the activity of probiotics during the drying process is retained as much as possible. The combination analysis module generates a variety of drying condition combinations through combinatorial methods and flexibly explores relatively optimal drying schemes, thereby improving the drying efficiency and product consistency. The post-drying analysis module uses convolutional neural network technology to calculate the brittleness index Chzs based on the monitored quality data and fits the balance evaluation index Pgzs, providing a scientific basis for evaluating product quality. Finally, the feedback module can judge the qualified status of the seaweed in real time by comparing it with the preset evaluation threshold W, and implement corresponding optimization measures for the unqualified status to ensure that the quality of the final product meets market demand. In summary, this system not only improves the controllability and reliability of the probiotic seaweed freeze-drying process, but also plays an important role in retaining the activity of probiotics and improving product quality, and has broad application prospects.

[0049] (2) The single drying condition difference analysis unit can effectively analyze the influence of a single parameter under different drying conditions by setting different parameter values ​​and monitoring the corresponding number of probiotic survival. This process provides a quantitative basis for subsequent in-depth analysis by calculating the inter-group difference value Zfc and the intra-group difference value Znc. Based on the above difference analysis results, the impact unit further calculates the influence coefficient Yxxs, making the evaluation of the influence of drying conditions on the activity of probiotics more comprehensive and accurate. This method combines the experimental database to make the analysis results more reliable and provide solid data support for subsequent screening. The preliminary screening unit sets a safety threshold and intelligently determines whether the influence coefficient Yxxs exceeds the threshold. If the safety threshold is exceeded, the system will promptly issue a range reduction instruction to adjust the drying conditions, thereby effectively reducing the negative impact on the probiotics. This dynamic feedback mechanism enables the system to quickly respond to potential risks and ensure the activity of the probiotics. In summary, the screening module ensures the quality and activity of probiotic seaweed during the freeze-drying process through systematic difference analysis and impact assessment.

[0050] (3) The range screening unit of the system further optimized the freeze-drying process of probiotic seaweed through an intelligent decision-making mechanism. After receiving the range reduction instruction, the range screening unit compared the number of surviving probiotics under the screened drying conditions with the preset activity requirements to ensure the rationality and effectiveness of the drying conditions. This dynamic screening process not only prevented the use of unqualified drying conditions, but also provided a basis for optimizing and improving drying parameters, which helped to improve the overall product quality and stability.

[0051] (4) The post-drying analysis module of the system not only simplifies the data analysis process through systematic quality monitoring and analysis methods, but also enables the impact of different parameters to be quantified, thereby more accurately analyzing and calculating the brittleness index. This comprehensive quality monitoring and analysis mechanism can timely detect and correct potential problems in the production process, ensuring that the probiotic seaweed maintains good flavor and taste while protecting the probiotic activity as much as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 The present invention is a block diagram of an intelligent control system for the freeze-drying process of probiotic seaweed. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Example 1

[0055] See also Figure 1 , the present invention provides an intelligent control system for the freeze-drying process of probiotic seaweed, including a pre-drying module, a preliminary experiment module, a screening module, a combination analysis module, a post-drying analysis module and a feedback module;

[0056] The preliminary experiment module is used to detect the number of surviving probiotics in the dried seaweed through the culture medium, and control different drying conditions to monitor the number of surviving probiotics in the dried seaweed in real time to build an experimental database;

[0057] The screening module is used to analyze the effects of different drying conditions on the activity of probiotics according to the experimental database to calculate the influence coefficient Yxxs, and preliminarily screen out the drying conditions that have an impact on the probiotics based on the numerical value of the influence coefficient Yxxs, and compare the number of probiotic survivals corresponding to the screened drying conditions with the preset activity requirements to screen out the range value of each single drying condition again;

[0058] The combination analysis module is used to filter out the range values ​​of each single drying condition in the screening module, generate a plurality of combined drying conditions through the combination operation in combinatorial science, and randomly extract a combined drying condition from the plurality of combined drying conditions to calculate and obtain the setting index Sdzs between the corresponding combined items;

[0059] The post-drying analysis module is used to monitor the relevant quality data information of the seaweed after freeze-drying, and analyze and calculate the brittleness index Chzs according to the relevant quality data information, and input the brittleness index Chzs and the set index Sdzs into the comprehensive quality prediction model constructed by using the convolutional neural network technology to fit the balance evaluation index Pgzs;

[0060] The feedback module is used to pre-set the evaluation threshold W, and compare and analyze it with the balance evaluation index Pgzs to comprehensively judge the qualified status of the current seaweed after freeze-drying, and take corresponding optimization measures according to the qualified status.

[0061] During the operation of this system, the system further realizes the precise monitoring and optimization control of the activity of probiotics through the organic combination of various modules. The preliminary experiment module detects the number of surviving probiotics in seaweed in real time and builds an experimental database, providing a reliable data basis for subsequent analysis. The screening module can effectively identify the influence of different drying conditions on the activity of probiotics, calculate the influence coefficient Yxxs, and then screen out the range of drying conditions that meet the activity requirements to ensure the effective survival of probiotics. The combination analysis module uses combination operations to generate a variety of drying condition combinations, and randomly extracts corresponding conditions to calculate the set index Sdzs, further improving the flexibility and efficiency of the drying process. The post-drying analysis module further realizes the multi-faceted evaluation of product quality by monitoring quality data and calculating the brittleness index Chzs, combining convolutional neural network technology to fit the balance evaluation index Pgzs. Finally, the feedback module adjusts the drying conditions in time by comparing the evaluation threshold W with Pgzs to ensure that the product meets the expected quality standards. The implementation of this system not only improves the nutritional value and market competitiveness of probiotic seaweed, but also optimizes the production process and further reduces resource waste.

[0062] Example 2

[0063] Please refer to Figure 1 ,Specifically: the preliminary experimental module includes a pre-drying unit and a condition testing unit;

[0064] The pre-drying unit is used to pre-coat the outer surface of the seaweed to be dried with a protective agent, wherein the protective agent includes glycerol and glucose, which can effectively protect the cell membrane of the probiotics and further reduce the damage during the freezing and drying process. At the same time, the number of surviving probiotics in the seaweed to be dried is detected by the culture medium, and the active probiotics are stained by combining the active staining method, and then the proportion of the active probiotics is monitored by the flow cytometer;

[0065] The condition testing unit is used to monitor the survival number of probiotics in the dried seaweed while controlling different drying conditions, and to match the survival number corresponding to each drying condition to construct an experimental database.

[0066] In this embodiment, the preliminary experimental module of the system further improves the survival rate and overall quality of probiotics in the freeze-drying process of probiotic seaweed through the effective combination of the pre-drying unit and the condition test unit. The pre-drying unit effectively protects the cell membrane of probiotics by coating the outer surface of the seaweed to be dried with a protective agent (such as glycerol and glucose), reducing the damage that may be caused during the freezing and drying process. This measure not only improves the survival rate of probiotics, but also lays a good foundation for the subsequent drying process. At the same time, the pre-drying unit detects the number of probiotics in the seaweed to be dried through the culture medium, and combines the active staining method to stain the active probiotics, and then uses the flow cytometer to monitor the proportion of active probiotics. This precise monitoring method makes the evaluation of the active state of probiotics more accurate and provides reliable data support for screening suitable drying conditions. The condition test unit monitors the number of probiotics in the seaweed to be dried in real time while controlling different drying conditions, ensuring systematic data recording and matching under various drying environments. This process constructs a detailed experimental database, which provides a valuable data basis for subsequent analysis and optimization. In summary, the preliminary experimental module determined the activity and survival rate of probiotics through precise monitoring and protection measures, creating favorable conditions for improving the quality and market competitiveness of probiotic seaweed.

[0067] Example 3

[0068] Please refer to Figure 1 ,Specifically: the screening module includes a single drying condition difference analysis unit, an impact unit, a preliminary screening unit and a range screening unit;

[0069] The single drying condition difference analysis unit is used to set different values ​​of the single parameter, and monitor the survival number of probiotics at each monitoring time point under different values, so as to analyze the difference of the single parameter under the drying conditions with different values, and respectively calculate and obtain the inter-group difference value Zfc and the intra-group difference value Znc, which are specifically obtained in the following manner:

[0070] ;

[0071] In the formula, n represents the number of groups of values ​​set for a single parameter, i=1, 2, 3, ..., n, is represented by the number of samples in the i-th group, It is expressed as the mean number of surviving probiotics in group i, It is expressed as the mean of the number of surviving probiotics in all groups in a single parameter;

[0072] ;

[0073] Where j = 1, 2, 3, ..., , It is expressed as the number of surviving probiotics at the jth monitoring time point in the i-th group.

[0074] The influence unit is used to analyze the influence of different drying conditions on the activity of probiotics according to the experimental database, based on the inter-group difference value Zfc and the intra-group difference value Znc, so as to calculate the influence coefficient Yxxs, which is specifically obtained by the following method:

[0075] ;

[0076] In the formula, n represents the number of groups of values ​​set for the single parameter; N represents the number of samples in all groups of the single parameter; Nn is used to determine the degrees of freedom of the within-group variance;

[0077] It should be noted that the degrees of freedom reflect the number of data points that can vary independently. In ANOVA, the degrees of freedom are used to describe the amount of independent information available when calculating variance.

[0078] The preliminary screening unit is used to pre-set a safety threshold, and compare and analyze the influence coefficient Yxxs with the safety threshold to preliminarily screen out the drying conditions that affect the probiotics. The specific contents are as follows:

[0079] If the influence coefficient Yxxs exceeds the safety threshold, it is preliminarily judged that the current single parameter has an impact on the probiotics, and a range reduction instruction will be issued at this time;

[0080] If the impact coefficient Yxxs does not exceed the safety threshold, it is preliminarily judged that the current single parameter has no impact on the probiotics.

[0081] In this embodiment, the screening module of the system further improves the optimization efficiency of the drying conditions of probiotic seaweed through the refined design of the single drying condition difference analysis unit, the influence unit, the preliminary screening unit and the range screening unit. First, the single drying condition difference analysis unit can systematically analyze the activity difference of probiotics under various drying conditions by setting different values ​​for single parameters and monitoring the survival number of probiotics, and obtain the difference values ​​between groups and within groups. This process provides a scientific basis for subsequent data analysis, so that researchers can clearly identify which drying conditions have a significant impact on the survival of probiotics. Then, the influence unit further analyzes the influence of drying conditions on the activity of probiotics based on the experimental database and the calculated difference values, and calculates the influence coefficient Yxxs. This numerical index enables researchers to intuitively evaluate the effectiveness of different drying conditions and provides data support for selecting relatively optimal conditions. The preliminary screening unit can quickly screen out the drying conditions that affect the probiotics by comparing with the preset safety threshold. When the influence coefficient Yxxs exceeds the safety threshold, the system will issue a range reduction instruction and adjust the drying conditions in time to ensure the survival and activity of probiotics. This dynamic adjustment capability effectively reduces the risk of damage to probiotics during the drying process. In summary, the screening module not only improves the quality control level of probiotic seaweed through systematic analysis and real-time feedback, but also provides a scientific basis for optimizing drying conditions, thereby enhancing the market competitiveness of probiotic seaweed.

[0082] Example 4

[0083] Please refer to Figure 1 Specifically: the range screening unit is used to compare the number of probiotic survivals corresponding to the screened drying conditions with the preset activity requirements after receiving the range reduction instruction, so as to screen out the range value of each single drying condition again, and the specific content is:

[0084] If the number of surviving probiotics corresponding to the screened drying conditions exceeds the preset activity requirement, the corresponding drying conditions are included in the range value of the corresponding single parameter;

[0085] If the number of surviving probiotics corresponding to the screened drying conditions does not exceed the preset activity requirement, the corresponding drying conditions will not be included in the range value of the corresponding single parameter.

[0086] In this embodiment, after receiving the range reduction instruction, the range screening unit of the system further optimizes the selection of drying conditions by accurately comparing the number of probiotics surviving under the screened drying conditions with the preset activity requirements. This mechanism ensures that the activity of probiotics in the freeze-drying process is effectively guaranteed. Specifically, when the number of probiotics surviving under the screened drying conditions exceeds the preset activity requirements, the system includes these conditions in the range value of the corresponding single parameter. This process not only enhances the scientificity and effectiveness of the drying conditions, but also provides a reliable operating basis for the subsequent drying process to ensure the quality of the final product. On the contrary, if the number of probiotics surviving under the screened drying conditions fails to meet the preset activity requirements, the system excludes these conditions from the range value. This decision-making mechanism can effectively avoid the influence of adverse conditions on the activity of probiotics, thereby ensuring the safety and activity of the product; in short, through this dynamic screening and adjustment method, the range screening unit provides an intelligent control means for the freeze-drying process of probiotic seaweed, so that the final product reaches a relatively good level in terms of nutrition and functionality.

[0087] Example 5

[0088] Please refer to Figure 1 Specifically: the combination analysis module is used to extract a combination item drying condition from a plurality of combination item drying conditions, and after dimensionless processing, to calculate and obtain the setting index Sdzs between the corresponding combination items, which is specifically obtained in the following manner:

[0089] ;

[0090] In the formula, Represented as the weight value of the kth single parameter, It is represented by the specific regulation value of the kth single parameter, K is represented by the number of single parameters, k=1, 2, 3, ..., K, where, The specific value is set by the user.

[0091] It should be noted that the individual parameters here include but are not limited to temperature, humidity, pressure, drying time, vacuum degree, oxygen concentration and lighting conditions.

[0092] In this embodiment, the combined analysis module of the system extracts a combined item from multiple combined item drying conditions and performs dimensionless processing, calculates the set index Sdzs, so that the impact of different drying conditions can be evaluated with a unified index, thereby providing a scientific basis for the subsequent selection of drying parameters. This mechanism can not only identify the drying conditions that are relatively favorable for the survival of probiotics, but also can be quickly adjusted under different experimental conditions to adapt to market demand and product characteristics. Changes. By implementing this combined analysis module, producers can more effectively design and adjust the drying process, thereby improving the activity and quality of probiotic seaweed. At the same time, the visualization and quantitative characteristics of the setting index Sdzs provide real-time feedback and optimization guidance for the production process, further ensuring the high standards of the final product in nutrition and taste. This systematic approach not only improves production efficiency, but also lays the foundation for the market competitiveness of probiotic seaweed.

[0093] Example 6

[0094] Please refer to Figure 1 , specifically: the post-drying analysis module includes a quality monitoring unit, a quality analysis unit and a comprehensive evaluation unit;

[0095] The quality monitoring unit is used to monitor the relevant quality data information of the seaweed after freeze-drying the seaweed to be dried using several groups of monitoring equipment, wherein the relevant quality data information includes vacuum degree Zkd, drying time Gsc and moisture content Shz.

[0096] The above vacuum degree Zkd can be monitored and obtained through a pressure sensor or a vacuum gauge;

[0097] Drying time Gsc is usually monitored by a timer or data logger;

[0098] The moisture content Shz can be monitored and obtained using a moisture measuring instrument, such as a Karl Fischer moisture meter or an infrared moisture analyzer;

[0099] The quality analysis unit is used to process the vacuum degree Zkd, drying time Gsc and moisture content Shz dimensionlessly according to the relevant quality data information, and map the corresponding data values ​​to the interval The embrittlement index Chzs is calculated by analysis, and the embrittlement index Chzs is obtained by the following method:

[0100] ;

[0101] In the formula, and are all weight values, C represents the first correction constant, where, and The specific value is set by the user.

[0102] In this embodiment, the quality monitoring unit obtains relevant quality data information of seaweed in real time through multiple groups of monitoring equipment, including vacuum degree, drying time and moisture content. This real-time monitoring ensures the accuracy and timeliness of quality data in the production process, and provides a solid foundation for subsequent analysis. The quality analysis unit performs dimensionless processing on the above data and maps it to a standardized interval to calculate the brittleness index Chzs. The calculation of this index uses weight values ​​and correction constants to make the analysis results more scientific and reliable. By quantifying the brittleness index Chzs, the system can objectively evaluate the impact of the drying process on the quality of seaweed, thereby providing a strong basis for optimizing drying conditions. Ultimately, this module can help producers effectively identify potential problems in the drying process, ensure the activity of probiotics and the taste quality of seaweed, and thus improve the consistency and market competitiveness of products. Through continuous quality monitoring and analysis, producers can adjust process parameters in time in actual production, ensure product quality and safety and consumer satisfaction as much as possible, and promote the sustainable development of the probiotic seaweed industry.

[0103] Example 7

[0104] Please refer to Figure 1 Specifically: the comprehensive evaluation unit is used to construct a comprehensive quality prediction model by using convolutional neural network technology, and input the embrittlement index Chzs and the set index Sdzs into the comprehensive quality prediction model, and after dimensionless processing, fit the balance evaluation index Pgzs, which is specifically obtained in the following way:

[0105] ;

[0106] In the formula, and are all weight values, G represents the second correction constant, where, and The specific value is set by the user.

[0107] Convolutional neural network technology is used to build an initial model, and the initial model is trained and tested with the experimental database and related quality data information. The trained initial model is used as a state recognition model, and feature information in the state recognition model is obtained respectively. The state recognition model is trained and tested with the obtained feature information. Combined with the range reduction instruction issued by the system, the trained state recognition model is used as a comprehensive quality prediction model.

[0108] The feedback module includes a comparison unit and an optimization feedback unit;

[0109] The comparison unit is used to compare and analyze the evaluation threshold W with the balance evaluation index Pgzs to comprehensively judge the qualified status of the current seaweed after freeze-drying. The specific comparison content is as follows:

[0110] If the balance evaluation index Pgzs does not exceed the evaluation threshold W, it is comprehensively judged that the current freeze-dried seaweed is not in a qualified state;

[0111] If the balance evaluation index Pgzs exceeds the evaluation threshold W, it is comprehensively judged that the current freeze-dried seaweed is in a qualified state;

[0112] The optimization feedback unit is used to take corresponding optimization measures according to the comparison results in the comparison unit, and the specific contents are as follows:

[0113] If it is not in qualified condition, the values ​​of each single parameter will be readjusted to prevent embrittlement and protect the activity of probiotics. At the same time, the air flow distribution during the freeze-drying process will be adjusted to ensure the uniformity of the air flow during the freeze-drying process and reduce hot spots. An alarm mechanism will be set to automatically record and prompt the operator when unqualified conditions are detected;

[0114] If it is in qualified condition, we will continue to use the current drying conditions to ensure the consistency of product quality, and regularly test the quality of the seaweed and the activity of probiotics to ensure long-term qualification. We will record the successful drying parameter settings and provide a reference for future production.

[0115] In this embodiment, the comprehensive evaluation unit of the system further improves the quality assessment ability of the probiotic seaweed freeze-drying process by using a comprehensive quality prediction model constructed by convolutional neural network technology. The model can accurately fit the balance evaluation index Pgzs through dimensionless processing of the brittleness index Chzs and the set index Sdzs, providing a scientific basis for subsequent quality judgment. This data-driven analysis method ensures the objectivity and accuracy of quality assessment and helps to quickly identify whether the product meets the standard. The feedback module clarifies the qualified status of the seaweed through comparative analysis, and then takes corresponding optimization measures. When the evaluation results show that the product is not up to standard, the system will automatically adjust various drying parameters to protect the activity of probiotics and reduce the risk of brittleness, while optimizing the airflow distribution to prevent the generation of hot spots. This real-time adjustment mechanism ensures the flexibility and safety of the production process. When the product is qualified, the system will continue to maintain the current drying conditions to ensure the consistency of product quality, and regularly detect the quality and probiotic activity of the seaweed. This long-term quality monitoring and data recording not only helps to improve production efficiency, but also provides valuable reference data for future production. Overall, the application of this system will significantly improve the production quality of probiotic seaweed, meet market demand, and enhance brand competitiveness.

[0116] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent control system for the freeze-drying process of probiotic seaweed, characterized in that: It includes preliminary experiment module, screening module, combination analysis module, post-drying analysis module and feedback module; The preliminary experiment module is used to detect the number of surviving probiotics in the dried seaweed through the culture medium, and control different drying conditions to monitor the number of surviving probiotics in the dried seaweed in real time to build an experimental database; The screening module is used to analyze the effects of different drying conditions on the activity of probiotics according to the experimental database to calculate the influence coefficient Yxxs, and preliminarily screen out the drying conditions that have an impact on the probiotics based on the numerical value of the influence coefficient Yxxs, and compare the number of probiotic survivals corresponding to the screened drying conditions with the preset activity requirements to screen out the range value of each single drying condition again; The combination analysis module is used to filter out the range values ​​of each single drying condition in the screening module, generate a plurality of combined drying conditions through the combination operation in combinatorial science, and randomly extract a combined drying condition from the plurality of combined drying conditions to calculate and obtain the setting index Sdzs between the corresponding combined items; The post-drying analysis module is used to monitor the relevant quality data information of the seaweed after freeze-drying, and analyze and calculate the brittleness index Chzs according to the relevant quality data information, and input the brittleness index Chzs and the set index Sdzs into the comprehensive quality prediction model constructed by using the convolutional neural network technology to fit the balance evaluation index Pgzs; The feedback module is used to pre-set the evaluation threshold W, and compare and analyze it with the balance evaluation index Pgzs to comprehensively judge the qualified status of the current seaweed after freeze-drying, and take corresponding optimization measures according to the qualified status.

2. The intelligent control system for the probiotic seaweed freeze-drying process according to claim 1, characterized in that: The preliminary experimental module includes a pre-drying unit and a condition testing unit; The pre-drying unit is used to pre-coat the outer surface of the seaweed to be dried with a protective agent, wherein the protective agent includes glycerol and glucose, and at the same time, the number of viable probiotics in the seaweed to be dried is detected by a culture medium, and the active probiotics are stained by an active staining method, and then the proportion of active probiotics is monitored by a flow cytometer; The condition testing unit is used to monitor the survival number of probiotics in the dried seaweed while controlling different drying conditions, and to match the survival number corresponding to each drying condition to construct an experimental database.

3. The intelligent control system for the probiotic seaweed freeze-drying process according to claim 2, characterized in that: The screening module includes a single drying condition difference analysis unit, an impact unit, a preliminary screening unit and a range screening unit; The single drying condition difference analysis unit is used to set different values ​​of the single parameter, and monitor the survival number of probiotics at each monitoring time point under different values, so as to analyze the difference of the single parameter under the drying conditions with different values, and respectively calculate and obtain the inter-group difference value Zfc and the intra-group difference value Znc, which are specifically obtained in the following manner: ； In the formula, n represents the number of groups of values ​​set for a single parameter, i=1, 2, 3, ..., n, is the number of samples in the i-th group, It is expressed as the mean number of surviving probiotics in group i, It is expressed as the mean of the number of surviving probiotics in all groups in a single parameter; ； Where j = 1, 2, 3, ..., , It is expressed as the number of surviving probiotics at the jth monitoring time point in the i-th group.

4. The intelligent control system for the probiotic seaweed freeze-drying process according to claim 3, characterized in that: The influence unit is used to analyze the influence of different drying conditions on the activity of probiotics according to the experimental database, based on the inter-group difference value Zfc and the intra-group difference value Znc, so as to calculate the influence coefficient Yxxs, which is specifically obtained by the following method: ； In the formula, n represents the number of groups of values ​​set for a single parameter; N represents the number of samples in all groups of a single parameter; The preliminary screening unit is used to pre-set a safety threshold, and compare and analyze the influence coefficient Yxxs with the safety threshold to preliminarily screen out the drying conditions that affect the probiotics. The specific contents are as follows: If the influence coefficient Yxxs exceeds the safety threshold, it is preliminarily judged that the current single parameter has an impact on the probiotics, and a range reduction instruction will be issued at this time; If the impact coefficient Yxxs does not exceed the safety threshold, it is preliminarily judged that the current single parameter has no impact on the probiotics.

5. The intelligent control system for the probiotic seaweed freeze-drying process according to claim 4, characterized in that: The range screening unit is used to compare the number of probiotic survivals corresponding to the screened drying conditions with the preset activity requirements after receiving the range reduction instruction, so as to screen the range value of each single drying condition again, and the specific content is: If the number of surviving probiotics corresponding to the screened drying conditions exceeds the preset activity requirement, the corresponding drying conditions are included in the range value of the corresponding single parameter; If the number of surviving probiotics corresponding to the screened drying conditions does not exceed the preset activity requirement, the corresponding drying conditions will not be included in the range value of the corresponding single parameter.

6. The intelligent control system for the probiotic seaweed freeze-drying process according to claim 1, characterized in that: The combination analysis module is used to extract a combination item drying condition from a plurality of combination item drying conditions, and after dimensionless processing, calculate and obtain the setting index Sdzs between the corresponding combination items, which is specifically obtained in the following manner: ； In the formula, Represented as the weight value of the kth single parameter, It represents the specific regulation value of the kth single parameter, K represents the number of single parameters, k=1, 2, 3, ..., K.

7. The intelligent control system for the probiotic seaweed freeze-drying process according to claim 1, characterized in that: The post-drying analysis module includes a quality monitoring unit, a quality analysis unit and a comprehensive evaluation unit; The quality monitoring unit is used to monitor the relevant quality data information of the seaweed after freeze-drying the seaweed to be dried using several groups of monitoring equipment, wherein the relevant quality data information includes vacuum degree Zkd, drying time Gsc and moisture content Shz.

8. The intelligent control system for the probiotic seaweed freeze-drying process according to claim 7, characterized in that: The quality analysis unit is used to process the vacuum degree Zkd, drying time Gsc and moisture content Shz dimensionlessly according to the relevant quality data information, and map the corresponding data values ​​to the interval The embrittlement index Chzs is calculated by analysis, and the embrittlement index Chzs is obtained by the following method: ； In the formula, and are all weight values, and C represents the first correction constant.

9. The intelligent control system for the probiotic seaweed freeze-drying process according to claim 8, characterized in that: The comprehensive evaluation unit is used to construct a comprehensive quality prediction model by using convolutional neural network technology, and input the embrittlement index Chzs and the set index Sdzs into the comprehensive quality prediction model. After dimensionless processing, the balance evaluation index Pgzs is fitted, which is specifically obtained in the following way: ； In the formula, and are all weight values, and G represents the second correction constant.

10. The intelligent control system for the probiotic seaweed freeze-drying process according to claim 1, characterized in that: The feedback module includes a comparison unit and an optimization feedback unit; The comparison unit is used to compare and analyze the evaluation threshold W with the balance evaluation index Pgzs to comprehensively judge the qualified status of the current seaweed after freeze-drying. The specific comparison content is as follows: If the balance evaluation index Pgzs does not exceed the evaluation threshold W, it is comprehensively judged that the current freeze-dried seaweed is not in a qualified state; If the balance evaluation index Pgzs exceeds the evaluation threshold W, it is comprehensively judged that the current freeze-dried seaweed is in a qualified state; The optimization feedback unit is used to take corresponding optimization measures according to the comparison results in the comparison unit, and the specific contents are as follows: If it is not in qualified condition, the value of each single parameter will be readjusted to prevent embrittlement and protect the activity of probiotics. At the same time, the air flow distribution during the freeze-drying process will be adjusted, and an alarm mechanism will be set. When unqualified conditions are detected, it will be automatically recorded and the operator will be prompted. If it is in qualified condition, the current drying conditions will continue to be used, the quality of the seaweed and the activity of probiotics will be tested regularly, and the successful drying parameter settings will be recorded.

Images