Ingredient calibration control system for feed production

By introducing a feed calibration control system that incorporates data acquisition, preprocessing, genetic algorithms, and knowledge graphs into feed production, the error problem of traditional manual feed batching methods has been solved, enabling precise control of feed ratios and stability of nutrient components, thereby improving production efficiency and quality.

CN119024803AInactive Publication Date: 2024-11-26HUANGSHAN DORUIER TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411516051.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-29
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional manual batching methods are prone to errors in feed production, resulting in uneven mixing, unstable quality, low efficiency, and difficulty in real-time monitoring of production.

Method used

A feed formulation calibration control system is adopted, which includes modules for data acquisition, preprocessing, feed ratio analysis, mapping, control, and human-computer interaction. It uses a genetic algorithm to obtain the optimal ratio combination and a knowledge graph to ensure that the nutrient composition meets the constraints. It is combined with a weighing module for precise control.

Benefits of technology

This enabled precise control of feed formulation, improved production quality and efficiency, ensured that nutritional components met standards, and enhanced the company's market competitiveness and production profits.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119024803A_ABST
    Figure CN119024803A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of feed production, and discloses an ingredient calibration control system for feed production, which comprises a data acquisition module, a data preprocessing module, a feed proportion analysis module, a feed proportion mapping module, a control module, a weighing module and a man-machine interaction module, a feed proportion analysis module and a feed proportion mapping module are arranged, so that the optimal feed proportion combination can be obtained through a genetic algorithm; according to the method, the nutritional ingredients of the feed optimal proportion combination are mapped, the knowledge graph is constructed, and the nutritional ingredients corresponding to the feed optimal proportion combination are obtained, so that the nutritional ingredients in feed production are ensured to reach the standard on the basis of ensuring the feed production profit, and the feed production quality is ensured; the combination of the two methods can obtain the profit maximization feed optimal ratio combination meeting the feed production quality, accurately analyzes and controls the feed ratio, obtains the optimal value of the feed ingredient ratio, and improves the feed production quality and efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of feed production, and more particularly to a batching calibration control system for feed production. Background Art

[0002] In the feed production process, the ratio of raw materials is crucial; the traditional manual mixing method is affected by subjective factors and is prone to errors, resulting in uneven mixing and unstable feed product quality, which reduces market competitiveness; at the same time, manual mixing requires a lot of manpower and time, is inefficient, and it is difficult to monitor production conditions in real time.

[0003] Therefore, a feed ingredient calibration control system is needed for feed production, which can obtain the optimal value of feed ingredient ratio based on intelligent algorithm, and then accurately control the feed ratio to improve the quality and efficiency of feed production. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides an ingredient calibration control system for feed production to solve the problems existing in the above-mentioned background technology.

[0005] The present invention provides the following technical solutions: a feed ingredient calibration control system for feed production, comprising a data acquisition module, a data preprocessing module, a feed ratio analysis module, a feed ratio mapping module, a control module, a weighing module and a human-computer interaction module; The data acquisition module is used to collect feed ratio information, raw material information and feed sales information, and transmit them to the data preprocessing module; The data preprocessing module is used to preprocess the data of the data acquisition module to obtain data that can be directly used; The feed ratio analysis module obtains the optimal feed ratio combination based on the genetic algorithm and transmits it to the feed ratio mapping module; The feed ratio mapping module maps the nutritional components of the optimal feed ratio combination, constructs a knowledge graph, obtains the nutritional components corresponding to the optimal feed ratio combination, and transmits the data to the control module if the constraint conditions are met; if the constraint conditions are not met, a feedback instruction is sent to the feed ratio analysis module; The control module is used to receive data from the feed ratio mapping module and control the weight of each ingredient in the feed ratio; The weighing module is used to weigh the weight of each ingredient through a weighing sensor. If the weight is consistent with the weight controlled by the control module, the weight of each ingredient is directly output to the human-computer interaction module; if the weight is inconsistent with the weight controlled by the control module, a calibration notification is sent to the human-computer interaction module and displayed; The human-computer interaction module is used to perform human-computer interaction display on the data.

[0006] Preferably, the specific method of the feed ratio analysis module to obtain the optimal feed ratio combination based on the genetic algorithm is: Step S01: Encode the feed ratio combination of each batch, obtain chromosomes, and construct an initial population; Step S02: Determine the fitness function; Step S03: Perform natural selection on chromosomes in the population; Step S04: performing crossover recombination on chromosomes in the population; Step S05: mutating the chromosomes in the population; Step S06: Obtain a new population, preset the population generation to be L, the fitness threshold to be Q, L is an integer greater than 0, and Q is a real number greater than 0; loop steps S03-S05 until the generation corresponding to the new population is L or the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold Q, the loop ends, and the feed ratio combination corresponding to the chromosome with the maximum fitness in the new population is used as the optimal feed ratio combination.

[0007] Preferably, in step S01, each batch of feed ratio combination is encoded as U, where U is a chromosome, and N chromosomes are randomly generated to form an initial population Z0, where Z0={U1, U2, U3, ..., U N}; In step S02, the fitness function is expressed as: , where S i is the fitness corresponding to the i-th chromosome, Pro i is the feed production profit of the batch corresponding to the i-th chromosome; i=1, 2, 3...N.

[0008] Preferably, in step S03, natural selection is performed by combining the elite method and the rotation method; wherein the elite method generates k1 offspring chromosomes, and for a population with a capacity of N, the fitness corresponding to the N chromosomes is arranged from large to small, and the k1 chromosomes at the front each generate a offspring chromosome; the rotation method generates k2 offspring chromosomes, that is, N chromosomes generate k2 offspring chromosomes according to the corresponding rotation probability; wherein k1 and k2 satisfy k1+k2=N, so as to keep the offspring population capacity N unchanged and the population increases in number of generations; The expression of the rotation probability is: , where P i is the rotation probability corresponding to the i-th chromosome.

[0009] Preferably, the Pro i The calculation formula is: , where s iis the sales volume of the batch of feed corresponding to the i-th chromosome, d i is the sales price of the batch of feed corresponding to the i-th chromosome, cos i It is the total production cost of the batch of feed corresponding to the i-th chromosome, that is, the sum of the total costs of all raw materials in the feed ratio combination corresponding to the i-th chromosome.

[0010] Preferably, the feed ratio mapping module maps the nutritional components of the optimal feed ratio combination in the following specific manner: Set the constraint y(j), where j is the jth constraint, and define a multidimensional matrix Mapping[U][Y(j)] to represent the mapping relationship, where U is the feed ratio combination code and Y(j) is the content of the nutrient component related to the jth constraint; A knowledge graph is constructed based on the feed ratio combination and the content of each nutrient component of each batch. The knowledge graph includes entities, entity attribute information, relationships between entities, and entity types. Entity attribute information is a label that describes entity attributes. The relationship between entities represents the semantic connection between different entities and describes various associations and interactions between entities in the knowledge graph. The entity type defines the category to which the entity belongs and defines the common attributes and relationships between entities. The optimal feed ratio combination is matched with the entities in the knowledge graph. The matching methods include string matching and semantic matching; string matching includes exact matching and approximate matching; after a successful match, the successfully matched entity in the knowledge graph is marked as a matching entity, that is, the content of each nutrient component is successfully matched, the matching entities obtained by the two methods are merged, and the entity attribute information corresponding to the matching entity is obtained from the knowledge graph.

[0011] Preferably, the feed ratio mapping module obtains the content of each nutrient component that successfully matches the optimal feed ratio combination, and if the set constraint conditions are met, transmits the feed optimal ratio combination data to the control module; if the set constraint conditions are not met, sends a feedback instruction to the feed ratio analysis module; After receiving the feedback instruction, the feed ratio analysis module removes the optimal ratio combination and continues to execute steps S01 to S06 to obtain a new optimal feed ratio combination and transmit it to the feed ratio mapping module to determine whether the new optimal feed ratio combination meets the set constraints.

[0012] Preferably, the feed ratio information is the historical data of the weight of each ingredient when each batch of feed is ratioed; the raw material information is the nutritional components contained in the feed ratio raw materials; and the feed sales information is the sales volume and unit price of each batch of feed.

[0013] Technical effects and advantages of the present invention: The present invention is advantageous for obtaining the best feed ratio combination through genetic algorithm by providing a feed ratio analysis module and a feed ratio mapping module; taking production profit as the formula of fitness function, the feed ratio combination with the highest profit rate is obtained as the best ratio combination, thereby improving the production efficiency of the enterprise; the feed ratio mapping module maps the nutritional components of the best feed ratio combination, and constructs a knowledge graph to obtain the nutritional components corresponding to the best feed ratio combination, and determines whether the constraint conditions are met. The enterprise can set different constraint conditions according to different situations, thereby ensuring that the nutritional components in feed production are up to standard on the basis of ensuring the profit of feed production, thereby ensuring the quality of feed production. The combination of the two can obtain the best profit-maximizing feed ratio combination that meets the quality of feed production. On the basis of intelligent algorithm, the feed ratio is accurately analyzed and controlled to obtain the optimal value of the feed ingredient ratio, thereby improving the quality and efficiency of feed production. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a structural diagram of the ingredient calibration control system for feed production of the present invention. DETAILED DESCRIPTION

[0015] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are only examples. The ingredient calibration control system for feed production involved in the present invention is not limited to the various structures recorded in the following embodiments. All other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0016] like Figure 1 As shown, the present invention provides a feed ingredient calibration control system for feed production, including a data acquisition module, a data preprocessing module, a feed ratio analysis module, a feed ratio mapping module, a control module, a weighing module and a human-computer interaction module; The data acquisition module is used to collect feed ratio information, raw material information and feed sales information, and transmit them to the data preprocessing module; the feed ratio information is the historical data of the weight of each ingredient when each batch of feed is mixed; the raw material information is the nutritional components contained in the feed ratio raw materials; the feed sales information includes but is not limited to the sales volume and sales unit price of each batch of feed; The data preprocessing module is used to preprocess the data of the data acquisition module to obtain data that can be used directly; the preprocessing operation includes but is not limited to cleaning and denoising the data; The feed ratio analysis module obtains the optimal feed ratio combination based on the genetic algorithm and transmits it to the feed ratio mapping module; The feed ratio mapping module maps the nutritional components of the optimal feed ratio combination, constructs a knowledge graph, obtains the nutritional components corresponding to the optimal feed ratio combination, and transmits the data to the control module if the constraint conditions are met; if the constraint conditions are not met, a feedback instruction is sent to the feed ratio analysis module; The control module is used to receive data from the feed ratio mapping module and control the weight of each ingredient in the feed ratio; The weighing module is used to weigh the weight of each ingredient through a weighing sensor. If it is consistent with the weight controlled by the control module, the weight of each ingredient is directly output to the human-computer interaction module; if it is inconsistent with the weight controlled by the control module, a calibration notification is sent to the human-computer interaction module and displayed; at this time, the staff needs to check and calibrate the weighing equipment. When the weight controlled by the control module is inconsistent with the weight weighed by the weighing module, it means that the weighing equipment has a deviation or the control module has a fault. If the weighing equipment is still inconsistent after checking and calibrating, the entire system needs to be tested; The human-computer interaction module is used to perform human-computer interaction display on the data.

[0017] In this embodiment, it should be specifically explained that the specific method for the feed ratio analysis module to obtain the optimal feed ratio combination based on the genetic algorithm is: Step S01: Encode each batch of feed ratio combination, obtain chromosomes, and construct an initial population; the feed ratio combination is the weight of each raw material in the feed ratio. For example, if the weight of each raw material in the feed ratio combination of the first batch is: soybean weight A, corn weight B, grain weight C, meat and bone meal weight D; then the feed ratio combination of this batch is coded as IABCD; Step S02: Determine the fitness function; Step S03: Perform natural selection on chromosomes in the population; Step S04: performing crossover recombination on chromosomes in the population; Step S05: mutating the chromosomes in the population; Step S06: obtaining a new population, with the preset population generation number being L, and the fitness threshold being Q, where L is an integer greater than 0, and Q is a real number greater than 0; looping through steps S03-S05 until the generation number corresponding to the new population is L or the fitness corresponding to a chromosome in the new population is greater than or equal to the fitness threshold Q, the loop ends, and the feed ratio combination corresponding to the chromosome with the maximum fitness in the new population is taken as the optimal feed ratio combination; illustratively, if the preset population generation number is 1, the chromosomes in the initial population are subjected to natural selection, crossover recombination, and a new population is obtained, and at this time the generation number corresponding to the new population is 1, so the loop ends; The fitness threshold Q is preset by those skilled in the art according to the algorithm accuracy. The population generation number L is obtained by those skilled in the art using a genetic algorithm multiple times under the conditions of multiple batches of different feed ratio combination data to obtain the best ratio combination. In each process of using the genetic algorithm, when the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold Q, the cycle ends and the generation number corresponding to the new population is obtained; the largest generation number among the multiple generations is taken as the population generation number L.

[0018] In this embodiment, it should be specifically explained that in step S01, each batch of feed ratio combination is encoded as U, where U is a chromosome, and N chromosomes are randomly generated to form an initial population Z0, where Z0={U1, U2, U3, ..., U N}; In step S02, the fitness function is expressed as: , where S i is the fitness corresponding to the i-th chromosome, Pro i is the feed production profit of the batch corresponding to the i-th chromosome; i=1, 2, 3...N; The Pro i The calculation formula is: , where s i is the sales volume of the batch of feed corresponding to the i-th chromosome, d i is the sales price of the batch of feed corresponding to the i-th chromosome, cos i is the total cost of feed production for the batch corresponding to the ith chromosome, that is, the sum of the total costs of all raw materials in the feed ratio combination corresponding to the ith chromosome. The cost of each raw material is different, and when the ratio weight is different, the cost of feed production is also different. Therefore, selecting the feed ratio combination with the maximum profit as the optimal feed ratio combination can improve production efficiency.

[0019] In this embodiment, it should be specifically explained that in step S03, natural selection is performed by combining the elite method and the rotation method; wherein the elite method generates k1 offspring chromosomes, and for a population with a capacity of N, the fitness corresponding to the N chromosomes is arranged from large to small, and the k1 chromosomes at the front each generate a offspring chromosome; the rotation method generates k2 offspring chromosomes, that is, N chromosomes generate k2 offspring chromosomes according to the corresponding rotation probability; wherein k1 and k2 satisfy k1+k2=N, so as to keep the offspring population capacity N unchanged and the population generation number increases; The expression of the rotation probability is: , where P i is the rotation probability corresponding to the i-th chromosome; In the step S04, L chromosomes are randomly selected from the population for crossover recombination to obtain L new chromosomes; the crossover recombination adopts the PMX method, which is a prior art and will not be described in detail in this embodiment; after the chromosome crossover recombination, the fitness of the L new chromosomes is calculated, and the fitness of the L new chromosomes and the fitness of the L chromosomes are sorted from large to small to generate a sorting table, and the L chromosomes in the sorting table are replaced with the L chromosomes in the population for crossover recombination in positive order; in this embodiment, L=0.7N is selected; In step S05, the mutation probability is preset to O, and the N chromosomes in the population are mutated according to the mutation probability. The mutation method is to randomly select the positions of two genes in the chromosome and exchange the values ​​of the two genes. In this embodiment, O=0.02 is selected; the mutation probability is preset by a person skilled in the art according to the algorithm efficiency and algorithm accuracy.

[0020] In this embodiment, it should be specifically explained that the specific manner in which the feed ratio mapping module maps the nutritional components of the optimal feed ratio combination is: Set a constraint y(j), where j is the jth constraint. The constraint may be one or more. The constraint is the minimum value of the content of one or more nutrients. The constraint and the minimum value may be set by a person skilled in the art according to actual conditions. For example, if there is only one constraint, which is that the calcium content in the nutrient must be greater than 5%, then the constraint can be expressed by the formula y(1)=5%. If there are multiple constraints, the constraints are recorded as y(1), y(2), ..., y(j) in descending order of the nutrient content. If the calcium content in the nutrient needs to be greater than 5%, the protein content needs to be greater than 3%, and the amino acid content needs to be greater than 4%, then the constraints are arranged in positive order as constraint y(1) on calcium content, constraint y(2) on amino acid content, and constraint y(3) on protein content, satisfying y(1)=5%, y(2)=3%, and y(3)=4%. A multidimensional matrix Mapping[U][Y(j)] is defined to represent the mapping relationship, wherein U is the feed ratio combination code, and Y(j) is the content of the nutrient component related to the j-th constraint condition. For example, if j=2, the multidimensional matrix is ​​represented as Mapping[U][Y(1)][Y(2)]. If the constraint conditions are the calcium content y(1) and the amino acid content y(2) in the nutrients, then Y(1) is the percentage value of the calcium content in the U-th feed ratio combination, and Y(1) is the percentage value of the amino acid content in the U-th feed ratio combination. A knowledge graph is constructed based on the feed ratio combination and the content of each nutrient component of each batch. The knowledge graph includes entities, entity attribute information, relationships between entities, and entity types. Entity attribute information is a label that describes entity attributes. The relationship between entities represents the semantic connection between different entities and describes various associations and interactions between entities in the knowledge graph. The entity type defines the category to which the entity belongs and defines the common attributes and relationships between entities. Match the best feed ratio combination with the entities in the knowledge graph, and the matching methods include string matching and semantic matching; string matching includes exact matching and approximate matching; exact matching is to compare the string corresponding to the best feed ratio combination with the string corresponding to the entity in the knowledge graph, and match them if they are exactly the same; approximate matching is to use a string similarity algorithm to calculate the similarity between the string corresponding to the best feed ratio combination and the string corresponding to the entity in the knowledge graph, and match the entity in the knowledge graph with the highest similarity with the best feed ratio combination; semantic matching is to use a word embedding method, which converts the best feed ratio combination and the entity in the knowledge graph into a vector form through a word embedding model, and matches them by calculating the similarity between the vectors; After the match is successful, the successfully matched entity in the knowledge graph is marked as a matching entity, that is, the content of each nutrient component is successfully matched, the matching entities obtained by the two methods are merged, and the entity attribute information corresponding to the matching entity is obtained from the knowledge graph.

[0021] In this embodiment, it should be specifically explained that the feed ratio mapping module obtains the content of each nutrient component successfully matched with the optimal feed ratio combination, and if the set constraint condition is met, the feed optimal feed ratio combination data is transmitted to the control module; if the set constraint condition is not met, a feedback instruction is sent to the feed ratio analysis module; illustratively, if the content of each nutrient component successfully matched with the optimal feed ratio combination has a content Y(j) related to the jth constraint condition < y(j), it is determined that the set constraint condition is not met; if the content Y(j) of all the nutrient components related to the jth constraint conditions in the content of each nutrient component successfully matched with the optimal feed ratio combination is greater than or equal to y(j), it is determined that the set constraint condition is met; After receiving the feedback instruction, the feed ratio analysis module removes the optimal ratio combination and continues to execute steps S01 to S06 to obtain a new optimal feed ratio combination and transmit it to the feed ratio mapping module to determine whether the new optimal feed ratio combination meets the set constraints.

[0022] In this embodiment, it should be specifically explained that the control module receives the optimal feed ratio combination data transmitted by the feed ratio analysis module, and controls the feed weight of each raw material according to the weight data of each raw material in the feed ratio.

[0023] In this embodiment, it should be specifically explained that the difference between this embodiment and the prior art mainly lies in that this embodiment is equipped with a feed ratio analysis module and a feed ratio mapping module, which is conducive to obtaining the optimal feed ratio combination through a genetic algorithm; the production profit is used as the formula of the fitness function, so as to obtain the feed ratio combination with the highest profit margin as the optimal ratio combination, thereby improving the production efficiency of the enterprise; the feed ratio mapping module maps the nutritional components of the optimal feed ratio combination, and constructs a knowledge graph to obtain the nutritional components corresponding to the optimal feed ratio combination, and determines whether the constraints are met. The enterprise can set different constraints according to different situations, thereby ensuring that the nutritional components in feed production are up to standard on the basis of ensuring the profit of feed production, thereby ensuring the quality of feed production. The combination of the two can obtain the optimal feed ratio combination that maximizes the profit of feed production quality. On the basis of the intelligent algorithm, the feed ratio is accurately analyzed and controlled to obtain the optimal value of the feed ingredient ratio, thereby improving the quality and efficiency of feed production.

[0024] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0025] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A batching calibration control system for feed production, characterized in that: It includes data acquisition module, data preprocessing module, feed ratio analysis module, feed ratio mapping module, control module, weighing module and human-computer interaction module; The data acquisition module is used to collect feed ratio information, raw material information and feed sales information, and transmit them to the data preprocessing module; The data preprocessing module is used to preprocess the data of the data acquisition module to obtain data that can be directly used; The feed ratio analysis module obtains the optimal feed ratio combination based on the genetic algorithm and transmits it to the feed ratio mapping module; The feed ratio mapping module maps the nutritional components of the optimal feed ratio combination, constructs a knowledge graph, obtains the nutritional components corresponding to the optimal feed ratio combination, and transmits the data to the control module if the constraint conditions are met; if the constraint conditions are not met, a feedback instruction is sent to the feed ratio analysis module; The control module is used to receive data from the feed ratio mapping module and control the weight of each ingredient in the feed ratio; The weighing module is used to weigh the weight of each ingredient through a weighing sensor. If the weight is consistent with the weight controlled by the control module, the weight of each ingredient is directly output to the human-computer interaction module; if the weight is inconsistent with the weight controlled by the control module, a calibration notification is sent to the human-computer interaction module and displayed; The human-computer interaction module is used to perform human-computer interaction display on the data.

2. The ingredient calibration control system for feed production according to claim 1, characterized in that: The specific method of the feed ratio analysis module to obtain the optimal feed ratio combination based on the genetic algorithm is: Step S01: Encode the feed ratio combination of each batch, obtain chromosomes, and construct an initial population; Step S02: Determine the fitness function; Step S03: Perform natural selection on chromosomes in the population; Step S04: performing crossover recombination on chromosomes in the population; Step S05: mutating the chromosomes in the population; Step S06: Obtain a new population, preset the population generation to be L, the fitness threshold to be Q, L is an integer greater than 0, and Q is a real number greater than 0; loop steps S03-S05 until the generation corresponding to the new population is L or the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold Q, the loop ends, and the feed ratio combination corresponding to the chromosome with the maximum fitness in the new population is used as the optimal feed ratio combination.

3. The ingredient calibration control system for feed production according to claim 2, characterized in that: In step S01, each batch of feed ratio combination is encoded as U, where U is a chromosome, and N chromosomes are randomly generated to form an initial population Z0, where Z0={U1, U2, U3, ..., U N }; In step S02, the fitness function is expressed as: , where S i is the fitness corresponding to the i-th chromosome, Pro i is the feed production profit of the batch corresponding to the i-th chromosome; i=1, 2, 3...N.

4. The ingredient calibration control system for feed production according to claim 2, characterized in that: In step S03, natural selection is performed by combining the elite method and the rotation method; wherein the elite method generates k1 offspring chromosomes, and for a population with a capacity of N, the fitness corresponding to the N chromosomes is arranged from large to small, and the k1 chromosomes at the front each generate a offspring chromosome; the rotation method generates k2 offspring chromosomes, that is, N chromosomes generate k2 offspring chromosomes according to the corresponding rotation probability; wherein k1 and k2 satisfy k1+k2=N, so as to keep the offspring population capacity N unchanged and the population generation number increases; The expression of the rotation probability is: , where P i is the rotation probability corresponding to the i-th chromosome.

5. The ingredient calibration control system for feed production according to claim 3, characterized in that: The Pro i The calculation formula is: , where s i is the sales volume of the batch of feed corresponding to the i-th chromosome, d i is the sales price of the batch of feed corresponding to the i-th chromosome, cos i It is the total production cost of the batch of feed corresponding to the i-th chromosome, that is, the sum of the total costs of all raw materials in the feed ratio combination corresponding to the i-th chromosome.

6. The ingredient calibration control system for feed production according to claim 1, characterized in that: The specific method in which the feed ratio mapping module maps the nutritional components of the optimal feed ratio combination is: Set the constraint y(j), where j is the jth constraint, and define a multidimensional matrix Mapping[U][Y(j)] to represent the mapping relationship, where U is the feed ratio combination code and Y(j) is the content of the nutrient component related to the jth constraint; A knowledge graph is constructed based on the feed ratio combination and the content of each nutrient component of each batch. The knowledge graph includes entities, entity attribute information, relationships between entities, and entity types. Entity attribute information is a label that describes entity attributes. The relationship between entities represents the semantic connection between different entities and describes various associations and interactions between entities in the knowledge graph. The entity type defines the category to which the entity belongs and defines the common attributes and relationships between entities. The optimal feed ratio combination is matched with the entities in the knowledge graph. The matching methods include string matching and semantic matching; string matching includes exact matching and approximate matching; after a successful match, the successfully matched entity in the knowledge graph is marked as a matching entity, that is, the content of each nutrient component is successfully matched, the matching entities obtained by the two methods are merged, and the entity attribute information corresponding to the matching entity is obtained from the knowledge graph.

7. The ingredient calibration control system for feed production according to claim 1, characterized in that: The feed ratio mapping module obtains the content of each nutrient component that successfully matches the optimal feed ratio combination, and if the set constraint conditions are met, transmits the feed optimal ratio combination data to the control module; if the set constraint conditions are not met, sends a feedback instruction to the feed ratio analysis module; After receiving the feedback instruction, the feed ratio analysis module removes the optimal ratio combination and continues to execute steps S01 to S06 to obtain a new optimal feed ratio combination and transmit it to the feed ratio mapping module to determine whether the new optimal feed ratio combination meets the set constraints.

8. The ingredient calibration control system for feed production according to claim 1, characterized in that: The feed ratio information is the historical data of the weight of each ingredient when each batch of feed is ratioed; the raw material information is the nutritional components contained in the feed ratio raw materials; and the feed sales information is the sales volume and unit price of each batch of feed.

Citation Information

Patent Citations

  • Intelligent proportioning method and system based on RFID (radio frequency identification) and data mining

    CN104574195A

  • Personalized nutrition guidance method and system based on machine learning

    CN116580817A

  • Method for optimizing cattle feed ratio based on hybrid genetic algorithm

    CN118133942A