Automatic gelatin feeding system and method

Abstract

The invention relates to the technical field of industrial automation, in particular to an automatic gelatin feeding system and method based on genetic algorithm and clustering algorithm optimization, and is specially used for a gelatin and auxiliary material feeding link in a medicinal capsule production process. The problems that in the prior art, the batching precision is insufficient, multi-formula switching is complex, the auxiliary material management efficiency is low, and intelligent optimization capacity is lacked are solved.

Description

Technical Field

[0001] The invention relates to the technical field of industrial automation, and in particular to an automatic gelatin feeding system and feeding method based on genetic algorithm and clustering algorithm optimization. Background Art

[0002] As a common drug carrier, pharmaceutical capsules are widely used because they can effectively protect drug ingredients and improve the patient's taking experience. In the production process of pharmaceutical capsules, the batching of gelatin and excipients is an important step in the entire production process. Its accuracy and efficiency are directly related to the quality and production cost of capsule products.

[0003] At present, the gelatin ingredients of pharmaceutical capsules face the following problems: Insufficient formulation accuracy: In the production of pharmaceutical capsules, the formulation of gelatin must be strictly followed in a specific ratio. However, in the traditional feeding method, there is a lot of manual participation or the semi-automatic equipment has insufficient precision, which can easily lead to ratio errors, thus affecting the solubility, stability and other key properties of the capsule.

[0004] Switching between multiple formulas is complex: The production of medicinal capsules requires frequent switching of formulas according to different specifications and uses (such as adjusting gelatin concentration, adding pigments or other excipients). Existing equipment takes a long time and generates a lot of waste when switching formulas, which reduces production efficiency.

[0005] Low efficiency in excipient management: The excipients involved in the production of medicinal capsules (such as plasticizers, pigments, flavorings, etc.) are of many types and complex characteristics. Different excipients have different requirements for storage conditions, feeding sequence and equipment parameters. The existing system is difficult to adjust flexibly, which increases the difficulty of management.

[0006] Lack of intelligent optimization capabilities: Traditional feeding systems generally use fixed programs to run, lack the ability to respond to the production environment (such as raw material characteristics, equipment status) in real time, and cannot achieve dynamic optimization through data-driven, resulting in low equipment utilization and waste of resources.

[0007] Pharmaceutical capsule manufacturers are in urgent need of a more intelligent and precise automatic feeding system to improve the accuracy of ingredients, increase production efficiency and adapt to complex multi-formula production needs. Based on this background, the intelligent feeding optimization technology combining genetic algorithm and clustering algorithm provides a new solution for the gelatin and excipient feeding system of pharmaceutical capsules. By optimizing the formula switching process and excipient grouping management, the production efficiency and adaptability of the system can be significantly improved, thereby meeting the high-precision and high-efficiency production needs in the field of pharmaceutical capsules. Summary of the invention

[0008] The present invention provides a gelatin automatic feeding system and feeding method based on genetic algorithm and clustering algorithm optimization, which is specially used for the gelatin and auxiliary material feeding link in the production process of medicinal capsules, so as to solve the problems of insufficient ingredient accuracy, complex switching of multiple recipes, low auxiliary material management efficiency and lack of intelligent optimization capability in the prior art.

[0009] The technical solution of the automatic gelatin feeding system of the present invention is as follows: A raw material storage and conveying module is used to store gelatin and auxiliary materials and convey them to the feeding device; Intelligent metering module, used to monitor and control the amount of each raw material in real time; Automatic mixing module, used to mix different raw materials; The control and data management module optimizes the feeding management plan by embedding genetic algorithms and clustering algorithms, including: Genetic algorithms are used to generate and optimize the feeding management plan for multi-recipe switching to minimize switching time, reduce raw material waste and improve equipment utilization; Clustering algorithms are used to group raw material attribute data to optimize raw material feeding sequence and equipment operating parameters; The human-computer interaction module is used to set the recipe, monitor the feeding process and display the system operation status.

[0010] Preferably, the genetic algorithm evaluates the fitness of the feeding management scheme of multi-recipe switching, taking the switching time, the amount of raw material waste and the equipment utilization rate as the optimization targets, and the fitness function formula is: ; in, is the switching time, W is the amount of raw material waste, U is the equipment utilization rate, , , is the weight coefficient.

[0011] Preferably, the clustering algorithm generates a feeding grouping management plan by clustering the raw material attribute data (including density, humidity, and viscosity), and the distance calculation formula is: ; in, is the raw material attribute feature vector, is the cluster center, m is the attribute dimension, Represents the eigenvalue of the i-th sample point in the k-th dimension; Represents the cluster center The eigenvalue in the kth dimension.

[0012] Preferably, when the genetic algorithm generates a feeding management plan, the recipe switching plan is optimized through a crossover operation, and the crossover formula is: ; ; in, , Feed management plan for the parent generation, , For the offspring feeding management plan, is the intersection point; represents a slice from index 0 to k−1, that is, the first k elements in the parent solution; represents the slice from index k to the end, that is, all elements from the kth element to the end in the parent scheme.

[0013] Preferably, the mutation operation of the genetic algorithm is optimized by randomly adjusting some parameters in the feeding management scheme, and the mutation formula is: ; in, is the jth parameter in the feeding management plan, and V is the value after mutation.

[0014] Preferably, the feeding grouping management scheme generated by the clustering algorithm is optimized by updating the clustering center, and the updating formula is: ; in, Cluster The new cluster centers of Cluster The set of sample points, Cluster The number of sample points.

[0015] Preferably, the control and data management module automatically adjusts the feeding operation of the equipment according to the optimal feeding management solution generated by the genetic algorithm, and reduces the frequency of equipment parameter adjustment in combination with the grouping result of the clustering algorithm.

[0016] Preferably, the human-computer interaction module supports remote monitoring and control, and realizes real-time data transmission and remote operation through the industrial Internet interface.

[0017] The feeding method of the gelatin automatic feeding system of the technical solution comprises the following steps: A. Raw material attribute collection: Collect attribute data of gelatin and excipients used in the production of pharmaceutical capsules, including but not limited to density, humidity and viscosity; B. Raw material grouping: Analyze the raw material attribute data through clustering algorithm, generate raw material grouping plan, optimize the raw material feeding sequence and equipment parameters, and the clustering calculation formula is: ; in, is the raw material attribute feature vector, is the cluster center, m is the attribute dimension, Represents the eigenvalue of the i-th sample point in the k-th dimension; Represents the cluster center The eigenvalue in the kth dimension; C. Feeding management plan generation: Generate the optimal feeding management plan for multi-recipe switching by combining the raw material grouping plan with the genetic algorithm, which specifically includes: The fitness function is set to optimize the switching time, raw material waste and equipment utilization rate. The formula is: ; in, is the switching time, W is the amount of raw material waste, U is the equipment utilization rate, , , is the weight coefficient; The feeding management plan is generated through the crossover and mutation operations of the genetic algorithm. The crossover formula is: ; ; in, , Feed management plan for the parent generation, , For the offspring feeding management plan, is the intersection point; represents a slice from index 0 to k−1, that is, the first k elements in the parent solution; represents a slice from index k to the end, that is, all elements from the kth element to the end in the parent scheme; D. Accurate feeding: According to the optimal feeding management plan, control the operating parameters of the intelligent metering module and the automatic mixing module, and accurately feed gelatin and auxiliary materials according to the formula requirements; E. Multi-recipe switching: After completing the feeding of the current recipe, adjust the equipment parameters according to the optimal feeding management plan to complete the efficient switching of multiple recipes; F. Data recording and feedback: Record real-time data during the feeding process, including feeding accuracy, switching efficiency and equipment utilization, and dynamically optimize the feeding management plan through genetic algorithms.

[0018] Preferably, the mutation operation of the genetic algorithm generates a new scheme by randomly adjusting the parameter values ​​in the feeding management scheme, and the mutation formula is: ; in, is the jth parameter in the feeding management plan, and V is the value after mutation.

[0019] The present invention achieves the following remarkable technical effects in the production process of medicinal capsules through the gelatin automatic feeding system optimized based on genetic algorithm and clustering algorithm: 1. The accuracy of ingredients is significantly improved The intelligent metering module combines with genetic algorithms to dynamically optimize the feeding management plan, so that the error of gelatin and excipients is controlled within ±0.5%, ensuring the formula accuracy and product consistency in the production process of medicinal capsules. It reduces quality problems caused by ratio errors and improves the solubility, stability and uniformity of the product.

[0020] 2. The efficiency of multi-recipe switching is greatly improved Genetic algorithms optimize the multi-recipe switching process, and by dynamically adjusting the switching sequence and equipment parameters, the switching time is shortened by about 30% and the waste of raw materials is reduced by about 20%. The system supports rapid response to multi-recipe production needs and meets the efficient production scenarios of multi-variety and small batches in the production of medicinal capsules.

[0021] 3. Intelligent management of auxiliary materials The clustering algorithm optimizes the grouping of raw material properties (such as density, humidity, viscosity, etc.), making the raw material grouping more reasonable and reducing the number of equipment adjustments by about 25%. It realizes the flexible allocation and management of different auxiliary materials, avoids equipment failures and operational errors caused by differences in raw material characteristics, and improves the stability of system operation.

[0022] 4. Advantages of the combination of two algorithms Global optimization capability of genetic algorithm: It can quickly generate and optimize the feeding management plan for multi-recipe switching and find the switching path with the highest overall production efficiency.

[0023] Characteristic data processing capabilities of clustering algorithms: Through accurate analysis of raw material properties, reasonable grouping is achieved, providing high-quality input data for genetic algorithms.

[0024] Algorithm synergy: The clustering algorithm provides a preliminary optimization basis for the genetic algorithm, which further adjusts the switching scheme through the genetic algorithm to form a closed-loop process from data grouping to global optimization.

[0025] This collaborative optimization method significantly improves the system's operating efficiency and adaptability, and provides an efficient solution for complex feeding scenarios in the production of medicinal capsules.

[0026] 5. System operation efficiency is significantly improved Through the combination of genetic algorithms and clustering algorithms, the system achieves real-time dynamic optimization of production conditions, increasing equipment utilization by about 15%-20%. The continuity and stability of system operation are greatly improved, downtime is reduced, and production efficiency is significantly improved.

[0027] 6. Improved intelligence and automation of production processes Intelligent generation and real-time adjustment of feeding management schemes reduce manual intervention and improve the system's adaptive ability. Equipped with human-computer interaction modules, it supports remote monitoring and operation, realizes data visualization management, and facilitates the control and traceability of the production process.

[0028] 7. Reduce production costs By reducing raw material waste, shortening switching time and improving equipment utilization, the raw material loss and energy consumption in the production process are significantly reduced, and the overall cost is reduced by about 10%-15%.

[0029] 8. Improve market competitiveness The system optimizes the production process of pharmaceutical capsules through precise ingredients and efficient management, providing enterprises with high-quality and efficient production guarantees in the pharmaceutical carrier market. The integration of the two algorithms enables the system to reach industry-leading levels in terms of intelligence and economy, and enhances the market competitiveness and brand value of enterprises.

[0030] The present invention not only solves the problems of inaccurate feeding, complex switching of multiple formulas, and inefficient management of auxiliary materials in the production of medicinal capsules, but also realizes intelligent optimization of the entire process through the synergy of genetic algorithms and clustering algorithms, providing the industry with an efficient, accurate and intelligent solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a structural block diagram of the present invention; Figure 2 It is a step diagram of the operating method of the present invention. DETAILED DESCRIPTION

[0032] Embodiment 1: The technical solution of the present embodiment is a gelatin automatic feeding system, which comprises: A raw material storage and conveying module is used to store gelatin and auxiliary materials and convey them to the feeding device; Intelligent metering module, used to monitor and control the amount of each raw material in real time; Automatic mixing module, used to mix different raw materials; The control and data management module optimizes the feeding management plan by embedding genetic algorithms and clustering algorithms, including: Genetic algorithms are used to generate and optimize the feeding management plan for multi-recipe switching to minimize switching time, reduce raw material waste and improve equipment utilization; Clustering algorithms are used to group raw material attribute data to optimize raw material feeding sequence and equipment operating parameters; The human-computer interaction module is used to set the recipe, monitor the feeding process and display the system operation status.

[0033] Embodiment 2: The difference between this embodiment and embodiment 1 is that this embodiment further includes: The genetic algorithm evaluates the fitness of the feeding management scheme of multi-recipe switching, with switching time, raw material waste and equipment utilization as optimization targets. The fitness function formula is: ; in, is the switching time, W is the amount of raw material waste, U is the equipment utilization rate, , , is the weight coefficient.

[0034] Preferably, the clustering algorithm generates a feeding grouping management plan by clustering the raw material attribute data (including density, humidity, and viscosity), and the distance calculation formula is: ; in, is the raw material attribute feature vector, is the cluster center, m is the attribute dimension, Represents the eigenvalue of the i-th sample point in the k-th dimension; Represents the cluster center The eigenvalue in the kth dimension.

[0035] Preferably, when the genetic algorithm generates a feeding management plan, the recipe switching plan is optimized through a crossover operation, and the crossover formula is: ; ; in, , Feed management plan for the parent generation, , For the offspring feeding management plan, is the intersection point; represents a slice from index 0 to k−1, that is, the first k elements in the parent solution; represents the slice from index k to the end, that is, all elements from the kth element to the end in the parent scheme.

[0036] Preferably, the mutation operation of the genetic algorithm is optimized by randomly adjusting some parameters in the feeding management scheme, and the mutation formula is: ; in, is the jth parameter in the feeding management plan, and V is the value after mutation.

[0037] Preferably, the feeding grouping management scheme generated by the clustering algorithm is optimized by updating the clustering center, and the updating formula is: ; in, Cluster The new cluster centers of Cluster The set of sample points, Cluster The number of sample points.

[0038] Preferably, the control and data management module automatically adjusts the feeding operation of the equipment according to the optimal feeding management solution generated by the genetic algorithm, and reduces the frequency of equipment parameter adjustment in combination with the grouping result of the clustering algorithm.

[0039] Preferably, the human-computer interaction module supports remote monitoring and control, and realizes real-time data transmission and remote operation through the industrial Internet interface.

[0040] Embodiment 3: This embodiment is a feeding method of a gelatin automatic feeding system, comprising the following steps: A. Raw material attribute collection: Collect attribute data of gelatin and excipients used in the production of pharmaceutical capsules, including but not limited to density, humidity and viscosity; B. Raw material grouping: Analyze the raw material attribute data through clustering algorithm, generate raw material grouping plan, optimize the raw material feeding sequence and equipment parameters, and the clustering calculation formula is: ; in, is the raw material attribute feature vector, is the cluster center, m is the attribute dimension, Represents the eigenvalue of the i-th sample point in the k-th dimension; Represents the cluster center The eigenvalue in the kth dimension; C. Feeding management plan generation: Generate the optimal feeding management plan for multi-recipe switching by combining the raw material grouping plan with the genetic algorithm, which specifically includes: The fitness function is set to optimize the switching time, raw material waste and equipment utilization rate. The formula is: ; in, is the switching time, W is the amount of raw material waste, U is the equipment utilization rate, , , is the weight coefficient; The feeding management plan is generated through the crossover and mutation operations of the genetic algorithm. The crossover formula is: ; ; in, , Feed management plan for the parent generation, , For the offspring feeding management plan, is the intersection point; represents a slice from index 0 to k−1, that is, the first k elements in the parent solution; represents a slice from index k to the end, that is, all elements from the kth element to the end in the parent scheme; D. Accurate feeding: According to the optimal feeding management plan, control the operating parameters of the intelligent metering module and the automatic mixing module, and accurately feed gelatin and auxiliary materials according to the formula requirements; E. Multi-recipe switching: After completing the feeding of the current recipe, adjust the equipment parameters according to the optimal feeding management plan to complete the efficient switching of multiple recipes; F. Data recording and feedback: Record real-time data during the feeding process, including feeding accuracy, switching efficiency and equipment utilization, and dynamically optimize the feeding management plan through genetic algorithms.

[0041] The mutation operation of the genetic algorithm generates a new scheme by randomly adjusting the parameter values ​​in the feeding management scheme. The mutation formula is: ; in, is the jth parameter in the feeding management scheme, and V is the value after mutation Embodiment 4: This embodiment is a specific application example of Embodiment 3, and is specifically as follows: Example Background A pharmaceutical capsule manufacturer needs to produce two capsule specifications: Recipe A: high concentration of gelatin (90%) and low concentration of glycerol (10%).

[0042] Formulation B: medium concentration of gelatin (70%), glycerin (20%) and pigment (10%).

[0043] Production requirements: 1. Each batch produces 100 kg, and the ratio error of each raw material is required to be controlled within ±0.5%.

[0044] 2. The recipe needs to be switched once every hour, and the switching time should be as short as possible to reduce the waste of raw materials.

[0045] 3. Raw material properties: Gelatin humidity is 12%-15%, glycerin has high viscosity, and pigment density is low, so equipment parameters need to be adjusted dynamically.

[0046] 1. Raw material attribute collection The sensor collects the property data of raw materials, including: Gelatin: humidity 12.5%, density 1.4 g / cm³, viscosity 0.5 Pa·s; Glycerin: humidity 0%, density 1.26 g / cm³, viscosity 0.89 Pa·s; Pigment: humidity 1%, density 1.2 g / cm³, viscosity 0.1 Pa·s.

[0047] 2. Raw material grouping The clustering algorithm is used to group the raw material attribute data. The steps are as follows: (1) Initialize cluster centers Select K=3 (3 categories) and randomly initialize 3 cluster centers: : Humidity 10%, density 1.3 g / cm³, viscosity 0.3 Pa·s; : Humidity 0%, density 1.25 g / cm³, viscosity 0.8 Pa·s; : Humidity 1%, density 1.2 g / cm³, viscosity 0.1 Pa·s.

[0048] (2) Calculate the distance from the sample to the cluster center Use the formula: ; Calculate gelatin, glycerin and pigment one by one , , distance.

[0049] Calculation results: Gelatin: classified as ; Glycerol: classified as ; Pigment: classified as .

[0050] (3) Update cluster centers Calculate the new cluster center of each group and finally generate a grouping scheme: Group 1 (moisture-sensitive group): gelatin; Group 2 (high viscosity group): glycerol; Group 3 (low density group): pigment.

[0051] Based on the grouping results, the device dynamically adjusts parameters: Gelatin: feeding speed 6 kg / min; Glycerol: feeding rate 8 kg / min; Pigment: feeding speed 10 kg / min.

[0052] 3. Generation of feeding management plan Genetic algorithm is used to generate the optimal feeding management plan for multi-recipe switching. The steps are as follows: (1) Setting the fitness function Optimization goal: ; in: T = 15 minutes (switching time); W = 3 kg (raw material waste); U=85% (equipment utilization rate).

[0053] (2) Crossover operation Randomly select two parent solutions: Parent 1: Recipe switching order A → B; Parent 2: Recipe switching order B → A.

[0054] Generate sub-schema: Offspring 1: A → B; Offspring 2: B → A.

[0055] 4. Accurate feeding Execute precise feeding according to the optimal solution: Formula A: Add 90 kg of gelatin and 10 kg of glycerin; Recipe B: Add 70 kg of gelatin, 20 kg of glycerin, and 10 kg of pigment.

[0056] The intelligent metering module monitors the feeding accuracy in real time, and the error is controlled within ±0.4%.

[0057] 5. Multiple recipe switching Complete recipe switching according to the optimal solution: Dynamically adjust device parameters; Cleaning time reduced from 12 minutes to 8 minutes; Switching time reduced from 15 minutes to 10 minutes; Raw material waste was reduced from 3 kg to 1 kg.

[0058] 6. Data recording and feedback Real-time recording: Feeding accuracy: error ±0.4%; Switching time: 10 minutes; Equipment utilization rate: 90%.

[0059] The system dynamically optimizes the fitness function by recording data, providing support for the next generation of optimization.

[0060] If there is a variation: Mutation Operation (1) Triggering mutation Perform mutation operations on the offspring solution with a probability of 10%: Original plan: A → B; Mutation plan: B → A.

[0061] (2) Adjust parameters To mutate the feeding speed: Original value: glycerol feeding rate 8 kg / min; After the change: glycerol feeding rate is 9 kg / min.

[0062] (3) Evaluation and retention Evaluate the mutation scheme through the fitness function: If the fitness of the variant solution is better than the current solution, it will be retained.

[0063] Example effect: Feeding accuracy: Feeding error is controlled within ±0.5%; Improved switching efficiency: switching time is reduced by 33%, and raw material waste is reduced by 66%; Improved equipment utilization: Through variation optimization, the equipment utilization rate reached 92%.

Claims

1. A gelatin automatic feeding system, characterized in that: The system includes: A raw material storage and conveying module is used to store gelatin and auxiliary materials and convey them to the feeding device; Intelligent metering module, used to monitor and control the amount of each raw material in real time; Automatic mixing module, used to mix different raw materials; The control and data management module optimizes the feeding management plan by embedding genetic algorithms and clustering algorithms, including: Genetic algorithms are used to generate and optimize the feeding management plan for multi-recipe switching to minimize switching time, reduce raw material waste and improve equipment utilization; Clustering algorithms are used to group raw material attribute data to optimize raw material feeding sequence and equipment operating parameters; The human-computer interaction module is used to set the recipe, monitor the feeding process and display the system operation status.

2. The automatic gelatin feeding system according to claim 1, characterized in that: The genetic algorithm evaluates the fitness of the feeding management scheme of multi-recipe switching, with switching time, raw material waste and equipment utilization as optimization targets. The fitness function formula is: ； in, is the switching time, W is the amount of raw material waste, U is the equipment utilization rate, , , is the weight coefficient.

3. The automatic gelatin feeding system according to claim 1, characterized in that: The clustering algorithm generates a feeding grouping management plan by clustering analysis of raw material attribute data. The clustering algorithm calculation formula is: ； in, is the raw material attribute feature vector, is the cluster center, m is the attribute dimension, Represents the eigenvalue of the i-th sample point in the k-th dimension; Represents the cluster center The eigenvalue in the kth dimension.

4. The automatic gelatin feeding system according to claim 1, characterized in that: When the genetic algorithm generates a feeding management plan, the recipe switching plan is optimized through a crossover operation, and the crossover formula is: ； ； in, , Feed management plan for the parent generation, , For the offspring feeding management plan, is the intersection point; represents a slice from index 0 to k−1, that is, the first k elements in the parent solution; represents a slice from index k to the end, that is, all elements from the kth element to the end in the parent's slice.

5. The automatic gelatin feeding system according to claim 1, characterized in that: The mutation operation of the genetic algorithm is optimized by randomly adjusting some parameters in the feeding management scheme, and its mutation formula is: ； in, is the jth parameter in the feeding management plan, and V is the value after mutation.

6. The automatic gelatin feeding system according to claim 3, characterized in that: The feeding grouping management scheme generated by the clustering algorithm is optimized by updating the clustering center, and the updating formula is: ； in, Cluster The new cluster centers of Cluster The set of sample points, Cluster The number of sample points.

7. The automatic gelatin feeding system according to claim 1, characterized in that: The control and data management module automatically adjusts the feeding operation of the equipment according to the optimal feeding management plan generated by the genetic algorithm, and reduces the frequency of equipment parameter adjustment in combination with the grouping result of the clustering algorithm.

8. The automatic gelatin feeding system according to claim 1, characterized in that: The human-computer interaction module supports remote monitoring and control, and realizes real-time data transmission and remote operation through the industrial Internet interface.

9. A feeding method for the automatic gelatin feeding system according to any one of claims 1 to 8, characterized in that: The following steps are involved: A. Raw material attribute collection: Collect attribute data of gelatin and excipients used in the production of pharmaceutical capsules, including but not limited to density, humidity and viscosity; B. Raw material grouping: Analyze the raw material attribute data through clustering algorithm, generate raw material grouping plan, optimize the raw material feeding sequence and equipment parameters, and the clustering calculation formula is: ； in, is the raw material attribute feature vector, is the cluster center, m is the attribute dimension, Represents the eigenvalue of the i-th sample point in the k-th dimension; Represents the cluster center The eigenvalue in the kth dimension; C. Feeding management plan generation: Generate the optimal feeding management plan for multi-recipe switching by combining the raw material grouping plan with the genetic algorithm, which specifically includes: The fitness function is set to optimize the switching time, raw material waste and equipment utilization rate. The formula is: ； in, is the switching time, W is the amount of raw material waste, U is the equipment utilization rate, , , is the weight coefficient; The feeding management plan is generated through the crossover and mutation operations of the genetic algorithm. The crossover formula is: ； ； in, , Feed management plan for the parent generation, , For the offspring feeding management plan, is the intersection point; represents a slice from index 0 to k−1, that is, the first k elements in the parent solution; represents a slice from index k to the end, that is, all elements from the kth element to the end in the parent scheme; D. Accurate feeding: According to the optimal feeding management plan, control the operating parameters of the intelligent metering module and the automatic mixing module, and accurately feed gelatin and auxiliary materials according to the formula requirements; E. Multi-recipe switching: After completing the feeding of the current recipe, adjust the equipment parameters according to the optimal feeding management plan to complete the efficient switching of multiple recipes; F. Data recording and feedback: Record real-time data during the feeding process, including feeding accuracy, switching efficiency and equipment utilization, and dynamically optimize the feeding management plan through genetic algorithms.

10. The feeding method of the gelatin automatic feeding system according to claim 9, characterized in that: The mutation operation of the genetic algorithm generates a new scheme by randomly adjusting the parameter values ​​in the feeding management scheme. The mutation formula is: ； in, is the jth parameter in the feeding management plan, and V is the value after mutation.

Images