A method for increasing the proportion of unsaturated fatty acids in sturgeon feed

Abstract

This invention discloses a method for increasing the proportion of unsaturated fatty acids in sturgeon compound feed, relating to the field of production control technology. The method involves pre-collecting raw material information and nutritional requirement information sets, constructing a formulation optimization model based on these sets, solving the optimization model using an optimization solver, iteratively solving and outputting the optimized formulation result, inputting the optimized formulation result into the production process system, and monitoring production process data in real time. Based on the production process monitoring data, a production stability fitness function is constructed, and based on the production stability fitness function and the production process monitoring data, a reinforcement learning model is used to adjust production parameters. This significantly increases the proportion of unsaturated fatty acids in the feed, ensuring the stability and consistency of feed quality.

Description

Technical Field

[0001] This invention relates to the field of production control technology, specifically a method for increasing the proportion of unsaturated fatty acids in sturgeon compound feed. Background Technology

[0002] Unsaturated fatty acids (UFAs) are a crucial nutrient in sturgeon formulated feed production, especially omega-3 and omega-6 fatty acids, which significantly contribute to sturgeon growth, development, immune function, and reproductive capacity. However, traditional sturgeon formulated feed production relies heavily on subjective experience and manual adjustments. Producers often select feed formulas and set production parameters based on experience, making it difficult to scientifically control the proportion of unsaturated fatty acids in the feed. The fluctuations and instabilities in these parameters during production can lead to inconsistent feed quality, further impacting the healthy growth of sturgeon.

[0003] Currently, the selection of feed formulations and the adjustment of production parameters in the feed production process mainly rely on the subjective experience of production personnel. Experienced technicians, through long-term practical experience, can ensure feed quality to a certain extent, but this method has significant limitations. First, subjective experience is difficult to quantify, and the experience levels of different producers vary greatly, leading to instability in feed quality. Second, experience-based methods are difficult to adapt to rapidly changing market demands and production environments, and cannot adjust and optimize feed formulations in a timely manner. Finally, manual adjustments are inefficient and make it difficult to automate and intelligentize the production process. To address these challenges, it is necessary to introduce scientific methods for formula optimization and production parameter optimization to improve the stability and efficiency of feed production.

[0004] Chinese patent application CN101209089A discloses a method for increasing n-3 polyunsaturated fatty acids in grass carp meat. The method involves feeding grass carp with hybrid Napier grass combined with commercially available freshwater fish feed. The dry matter weight ratio of the feed and the hybrid Napier grass is 1.1:1. However, this method fails to control production parameters from a data processing perspective.

[0005] Therefore, this invention proposes a method for increasing the proportion of unsaturated fatty acids in sturgeon compound feed. Summary of the Invention

[0006] This invention aims to at least solve one of the technical problems existing in the prior art. To this end, this invention proposes a method for increasing the proportion of unsaturated fatty acids in sturgeon compound feed, which significantly increases the proportion of unsaturated fatty acids in the feed and ensures the stability and consistency of feed quality.

[0007] To achieve the above objectives, a method for increasing the proportion of unsaturated fatty acids in sturgeon formulated feed is proposed, comprising the following steps:

[0008] Step 1: Pre-collect information on raw materials and nutritional requirements;

[0009] Step 2: Based on the raw material information set and nutritional requirement information set, construct a formula optimization model;

[0010] Step 3: Use an optimization solver to solve the formula optimization model, and iteratively solve to output the optimized formula results;

[0011] Step 4: Input the optimized formula results into the production process system and monitor the production process data in real time.

[0012] Step 5: Construct a production stability fitness function based on production process monitoring data;

[0013] Step Six: Based on the production stability fitness function and production process monitoring data, use a reinforcement learning model to adjust production parameters.

[0014] The method for collecting the raw material information set is as follows:

[0015] In the laboratory, analytical instruments were used to analyze and test the nutritional components and physicochemical properties of various raw materials used to produce sturgeon compound feed.

[0016] Collect economic parameters for each raw material based on market pricing;

[0017] The nutritional component data, the physicochemical properties, and the economic parameters constitute the raw material information set.

[0018] The method for collecting the nutritional requirements information set is as follows:

[0019] The growth process of sturgeon is divided into stages to obtain a list of growth stages;

[0020] For each growth stage, the nutritional requirements of various nutrient factors were statistically analyzed.

[0021] The method for constructing the formula optimization model based on the raw material information set and the nutritional requirement information set is as follows:

[0022] The different growth stages of the sturgeon are numbered as k;

[0023] Label the number of each raw material in the production formula as i, and label the quantity of all raw material types as I;

[0024] The unit content of unsaturated fatty acids in the i-th raw material is labeled as UNi;

[0025] Label the numbers of all nutrients other than unsaturated fatty acids in the nutritional composition data as j; label the quantities of all nutrients other than unsaturated fatty acids as J;

[0026] The unit content of the j-th nutrient element in the i-th raw material is labeled as Nij;

[0027] Set a preset target ratio UTk of unsaturated fatty acids for the k-th growth stage;

[0028] For the k-th growth stage, set the preset target ratio Tkj for the j-th nutrient element;

[0029] The unit cost of raw material i is denoted as Ci, and the cost budget per unit quantity of compound feed is denoted as Cmax;

[0030] For the i-th raw material in the k-th growth stage, set the formula ratio variable xki;

[0031] For the k-th growth stage, the minimum required contents of unsaturated fatty acids and the j-th nutrient element are set as UDk and Dkj, respectively.

[0032] For the k-th growth stage:

[0033] Based on the unit content of unsaturated fatty acids, the unit content of nutrients, the preset target ratio of unsaturated fatty acids, the preset target ratio of nutrients, and the formula ratio variables, a formula objective function is constructed.

[0034] Based on the formula ratio variables, the minimum required content of unsaturated fatty acids and the j-th nutrient element, the unit cost and cost budget of each raw material, a set of constraints is constructed.

[0035] The linear programming model constructed with maximizing the formula objective function as the optimization objective and the set of constraints as constraints serves as the formula optimization model.

[0036] The method of using an optimization solver to solve the formulation optimization model and iteratively solving to output the optimized formulation result is as follows:

[0037] For the various growth stages of sturgeon:

[0038] The linear programming solver is used to solve the formula optimization model corresponding to the growth stage, and the variable values ​​of the formula ratio variables of each raw material are obtained; the variable values ​​of the formula ratio variables of each raw material constitute the optimized formula result.

[0039] The result of inputting the optimized formula into the production process system is:

[0040] Based on the specific growth stage of the sturgeon to be raised, the raw materials are proportioned according to the variable values ​​of the formula ratio of each raw material in the optimized formula results for the corresponding growth stage, so as to obtain the raw materials for the production of the mixed feed.

[0041] The method for real-time monitoring of production process data is as follows:

[0042] The content of unsaturated fatty acids in mixed raw materials during the production of compound feed is monitored in real time using spectral analysis technology.

[0043] Through sensors of various physical parameters, real-time parameter values ​​of various physical parameters are collected during the production process of compound feed.

[0044] Real-time unsaturated fatty acid content and real-time values ​​of various physical parameters constitute the production process monitoring data.

[0045] The method for constructing the production stability fitness function based on production process monitoring data is as follows:

[0046] The initial time of compound feed production is marked as 0:

[0047] Mark any point in the production of compound feed as t;

[0048] The physical parameters are labeled as p;

[0049] The standard deviation of the p-th physical parameter from time 0 to time t is denoted as . ;

[0050] Based on the standard deviation of each physical parameter, a production stability fitness function is constructed.

[0051] The method of adjusting production parameters using a reinforcement learning model based on the production stability fitness function and production process monitoring data is as follows:

[0052] The reinforcement learning model is set as the Actor-Critic model;

[0053] Define the state space, action space, and reward function of the reinforcement learning model;

[0054] The state space includes the content of unsaturated fatty acids at any time t during the production process, as well as the real-time parameter values ​​of various physical parameters.

[0055] The action space includes the adjustment amount of all controlled production parameters;

[0056] The reward function is a weighted sum of the production stability fitness function and the unsaturated fatty acid consumption value, wherein the weight of the unsaturated fatty acid consumption value is negative and all weights are preset values.

[0057] Initialize the model parameters of the Actor and Critic networks, and set the optimizer to the Adam optimizer;

[0058] At each time t:

[0059] The current state is obtained from the environment, an action is selected using the Actor network, and the selected action is executed to observe the state at the next moment and calculate the reward value. The experience is stored in the experience replay buffer, and the experience includes the current state, the selected action, the state at the next moment, and the reward value.

[0060] A batch of experiences is randomly sampled from the experience replay buffer, and the target Q value is calculated;

[0061] The mean squared error function is used as the loss function for the Critic network model; the parameters of the Critic network are updated using a soft update strategy.

[0062] Through multiple iterations and updates, production parameters are optimized to maximize the reward function.

[0063] A computer-readable storage medium is proposed, on which an erasable and rewritable computer program is stored;

[0064] When the computer program is run on a computer device, the computer device performs the above-described method for increasing the proportion of unsaturated fatty acids in sturgeon compound feed.

[0065] Compared with the prior art, the beneficial effects of the present invention are:

[0066] This invention pre-collects raw material information and nutritional requirement information sets. Based on these sets, a formulation optimization model is constructed. An optimization solver is used to solve the model, iteratively solving and outputting the optimized formulation result. This result is then input into the production process system. Real-time monitoring of production process data is conducted. Based on this data, a production stability fitness function is constructed. Using this fitness function and the monitoring data, a reinforcement learning model is used to adjust production parameters. Raw material and nutritional requirement information is collected and analyzed to construct a fitness function. A linear programming solver is used to optimize the formulation combination, ensuring that the unsaturated fatty acid content in the feed reaches the target value. During production parameter optimization, a state space, action space, and reward function are defined. A production stability fitness function is constructed, and an Actor-Critic model is trained. Through parameter tuning and model optimization, automation and intelligence in sturgeon feed production are achieved, significantly increasing the proportion of unsaturated fatty acids in the feed and ensuring the stability and consistency of feed quality. Attached Figure Description

[0067] Figure 1 This is a flowchart of a method for increasing the proportion of unsaturated fatty acids in sturgeon compound feed according to Embodiment 1 of the present invention;

[0068] Figure 2This is an example diagram illustrating the unsaturated fatty acid requirements of sturgeon at various growth stages in Embodiment 1 of the present invention. Detailed Implementation

[0069] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0070] Example 1

[0071] like Figure 1 As shown, a method for increasing the proportion of unsaturated fatty acids in sturgeon formulated feed includes the following steps:

[0072] Step 1: Pre-collect information on raw materials and nutritional requirements;

[0073] Step 2: Based on the raw material information set and nutritional requirement information set, construct a formula optimization model;

[0074] Step 3: Use an optimization solver to solve the formula optimization model, and iteratively solve to output the optimized formula results;

[0075] Step 4: Input the optimized formula results into the production process system and monitor the production process data in real time.

[0076] Step 5: Construct a production stability fitness function based on production process monitoring data;

[0077] Step Six: Based on the production stability fitness function and production process monitoring data, use a reinforcement learning model to adjust production parameters.

[0078] The method for collecting the raw material information set is as follows:

[0079] In the laboratory, analytical instruments were used to analyze and test the nutritional components and physicochemical properties of various raw materials used to produce sturgeon compound feed.

[0080] Collect economic parameters for each raw material based on market pricing;

[0081] The nutritional component data, the physicochemical properties, and the economic parameters constitute the raw material information set.

[0082] Specifically, the analytical instruments include a gas chromatograph or a liquid chromatograph, which are used to analyze the nutritional components and physicochemical properties of the raw materials, respectively.

[0083] The nutritional data includes protein content, fat content, the content of various types of unsaturated fatty acids, such as the specific content of ω-3 fatty acids and ω-6 fatty acids, as well as the content of other key nutrients, such as vitamins, minerals, and fiber.

[0084] The physicochemical properties include moisture content, particle size distribution, and antioxidant properties;

[0085] The economic parameters include the cost of each raw material.

[0086] It should be noted that the collection of nutritional data not only needs to ensure the proportion of unsaturated fatty acids in the subsequent formula optimization process, but also needs to ensure that the designed feed formula can meet the nutritional needs of sturgeon at each growth stage and promote their healthy growth and reproduction.

[0087] The collection of physicochemical properties is necessary to ensure the stability, palatability, and processing performance of compound feed, thereby improving the overall quality of the feed.

[0088] Economic parameters can help to reasonably control feed production costs and ensure production sustainability while meeting nutritional requirements.

[0089] The method for collecting the nutritional requirements information set is as follows:

[0090] The growth process of sturgeon is divided into stages to obtain a list of growth stages;

[0091] Specifically, such as Figure 2 The diagram illustrates the requirements of sturgeon for unsaturated fatty acids at different growth stages, including juvenile, adult, and reproductive stages. The required proportions of unsaturated fatty acids vary at each stage. For example, in the juvenile stage, the requirement for ω-3 unsaturated fatty acids is 2%-3%, and the requirement for ω-6 unsaturated fatty acids is 1-2%. In the adult stage, the requirement for ω-3 unsaturated fatty acids is 1%-2%, and the requirement for ω-6 unsaturated fatty acids is 0.5-1.5%. In the reproductive stage, the requirement for ω-3 unsaturated fatty acids is 3%-4%, and the requirement for ω-6 unsaturated fatty acids is 1-3%. Therefore, it is necessary to optimize the formulation of feed for each growth stage.

[0092] For each growth stage, the nutritional requirements of various factors are statistically analyzed by consulting scientific literature or through feeding experience.

[0093] Specifically, the nutritional factors include protein requirements, fat requirements, unsaturated fatty acid requirements, carbohydrate requirements, vitamin requirements, and mineral requirements.

[0094] Furthermore, the method for constructing the formula optimization model based on the raw material information set and the nutritional requirement information set is as follows:

[0095] The different growth stages of the sturgeon are numbered as k;

[0096] Label the number of each raw material in the production formula as i, and label the quantity of all raw material types as I;

[0097] The unit content of unsaturated fatty acids in the i-th raw material is labeled as UNi;

[0098] Label the numbers of all nutrients other than unsaturated fatty acids in the nutritional composition data as j; label the quantities of all nutrients other than unsaturated fatty acids as J;

[0099] The unit content of the j-th nutrient element in the i-th raw material is labeled as Nij;

[0100] Set a preset target ratio UTk of unsaturated fatty acids for the kth growth stage. It is understandable that unsaturated fatty acids are consumed during the production of compound feed. Therefore, in order to increase the proportion of unsaturated fatty acids in the compound feed, the value of UT needs to be set to be greater than the upper limit of the required proportion of unsaturated fatty acids in this production stage. For example, the value of UT in the juvenile stage should be greater than 5% (the sum of the upper limits of ω-3 unsaturated fatty acids and ω-6 unsaturated fatty acids).

[0101] For the k-th growth stage, set the preset target ratio Tkj for the j-th nutrient element;

[0102] The unit cost of raw material i is denoted as Ci, and the cost budget per unit quantity of compound feed is denoted as Cmax;

[0103] For the i-th raw material in the k-th growth stage, set the formula ratio variable xki;

[0104] For the k-th growth stage, the minimum required contents of unsaturated fatty acids and the j-th nutrient element are set as UDk and Dkj, respectively.

[0105] For the k-th growth stage:

[0106] Based on the unit content of unsaturated fatty acids, the unit content of nutrients, the preset target ratio of unsaturated fatty acids, the preset target ratio of nutrients, and the formula ratio variables, a formula objective function is constructed.

[0107] Based on the formula ratio variables, the minimum required content of unsaturated fatty acids and the j-th nutrient element, the unit cost and cost budget of each raw material, a set of constraints is constructed.

[0108] The linear programming model constructed with maximizing the formula objective function as the optimization objective and the set of constraints as constraints serves as the formula optimization model.

[0109] Preferably, the expression for the formulation objective function can be constructed as follows:

[0110] The objective function for the formulation of the k-th growth stage is denoted as Fk;

[0111] The formula for the objective function Fk of the formulation is then set as follows:

[0112] ; where w0 and wj are both preset proportion coefficients; it can be understood that the first term in the expression of the formula objective function Fk measures the difference between unsaturated fatty acids and the target proportion, and the second term measures the difference between various other nutrients and their corresponding target proportions. Therefore, maximizing Fk takes into account both the goal of increasing the proportion of unsaturated fatty acids and the nutritional balance of other nutrients.

[0113] The set of constraints can be constructed as follows:

[0114] The set of constraints for the k-th growth stage is labeled Uk;

[0115] The constraints included in Uk are:

[0116] The constraint is that the unit content of unsaturated fatty acids must not be lower than the minimum required content.

[0117] The constraint is that the total content of any j-th nutrient element must not be lower than the minimum required content corresponding to the j-th nutrient element.

[0118] The constraint is that the sum of the proportions of all raw materials should be 1.

[0119] Cost constraints per unit quantity of compound feed.

[0120] Furthermore, the method of using an optimization solver to solve the formulation optimization model and iteratively solving to output the optimized formulation results is as follows:

[0121] For the various growth stages of sturgeon:

[0122] The formula optimization model corresponding to this growth stage is solved using a linear programming solver to obtain the variable values ​​of the formula ratio variables of each raw material; the variable values ​​of the formula ratio variables of each raw material constitute the optimized formula result; the linear programming solver includes, but is not limited to, existing tools such as CPlex and Gurobi;

[0123] Generally, since linear programming problems are non-NP-hard problems and can be solved in polynomial time, linear programming solvers can find the optimal solution of the recipe optimization model, that is, the optimized recipe result is essentially the optimal recipe of the recipe optimization model.

[0124] Furthermore, the input of the optimized formula result into the production process system is as follows:

[0125] Based on the specific growth stage of the sturgeon to be raised, the raw materials are proportioned according to the variable values ​​of the formula ratio of each raw material in the optimized formula results for the corresponding growth stage, so as to obtain the raw materials for the production of the mixed compound feed; thus providing a basis for the subsequent production of compound feed.

[0126] Furthermore, the method for real-time monitoring of production process monitoring data is as follows:

[0127] The content of unsaturated fatty acids in the mixed raw materials during the production of compound feed is monitored in real time using spectral analysis technology; specifically, the spectral analysis technology can be near-infrared spectroscopy or Raman spectroscopy.

[0128] Through sensors of various physical parameters, real-time parameter values ​​of various physical parameters are collected during the production process of compound feed.

[0129] Real-time unsaturated fatty acid content and real-time values ​​of various physical parameters constitute the production process monitoring data.

[0130] Specifically, the physical parameters include temperature, humidity, pressure, oil application amount, raw material flow rate, and power consumption. Among these physical parameters, temperature, pressure, and oil application amount are adjustable parameters, and all of these physical parameters need to be kept stable during the production process.

[0131] Furthermore, the method for constructing the production stability fitness function based on production process monitoring data is as follows:

[0132] The initial time of compound feed production is marked as 0:

[0133] Mark any point in the production of compound feed as t;

[0134] The physical parameters are labeled as p;

[0135] The standard deviation of the p-th physical parameter from time 0 to time t is denoted as . ;

[0136] Based on the standard deviation of various physical parameters, a production stability fitness function is constructed.

[0137] Preferably, the production stability fitness function can be constructed as follows:

[0138] The production stability fitness function is denoted as G;

[0139] The expression for the production stability fitness function G can then be set as: It is understandable that by maximizing the production stability fitness function G, the stability of the production process can be controlled, thereby improving the production quality of compound feed.

[0140] Furthermore, the method of adjusting production parameters using a reinforcement learning model based on the production stability fitness function and production process monitoring data is as follows:

[0141] The reinforcement learning model is set as the Actor-Critic model;

[0142] Define the state space, action space, and reward function of the reinforcement learning model;

[0143] The state space includes the content of unsaturated fatty acids at any time t during the production process, as well as the real-time parameter values ​​of various physical parameters.

[0144] The action space includes the adjustable amounts of all controllable production parameters; for example, increasing the temperature by 0.5 degrees Celsius, decreasing it by 0.5 degrees Celsius, increasing it by 1 degree Celsius, etc., to describe how to change the current production state;

[0145] The reward function is a weighted sum of the production stability fitness function and the unsaturated fatty acid consumption value, wherein the weight of the unsaturated fatty acid consumption value is negative and all weights are preset values; the unsaturated fatty acid consumption value is the difference between the unsaturated fatty acid at the current time and the unsaturated fatty acid at the previous time. The larger the difference, the greater the loss of unsaturated fatty acids.

[0146] Initialize the model parameters of the Actor and Critic networks, and set the optimizer to the Adam optimizer;

[0147] At each time t:

[0148] Obtain the current state from the environment, select an action using the Actor network, execute the selected action, observe the state at the next moment, calculate the reward value, and store the experience (current state, selected action, state at the next moment, reward value) in the experience replay buffer;

[0149] A batch of experiences is randomly sampled from the experience replay buffer, and the target Q value is calculated;

[0150] Wherein, the target Q value is ;in, Let γ be the target Q value, and γ be the discount factor. Rt is the estimated value output by the Critic network, and Rt is the reward value.

[0151] The mean squared error function is used as the loss function for the Critic network model; the parameters of the Critic network are updated using a soft update strategy.

[0152] Through multiple iterations, the Actor-Critic model gradually learns to optimize production parameters to maximize the reward function.

[0153] The following are the experimental setup and conclusions during the implementation of this invention, illustrating that the solution of this invention achieves the expected technical effect:

[0154] I. Experimental Objectives

[0155] 1. Core Validation:

[0156] Can the invented method (formula optimization + parameter reinforcement learning) significantly increase the ω-3 / ω-6 fatty acid ratio in sturgeon feed? Can intelligent control of production parameters reduce fluctuations in physical parameters and improve production stability? What are the comprehensive advantages of this method in terms of economy (cost) and sturgeon growth performance?

[0157] 2. Detailed Validation:

[0158] The impact of formulation optimization on nutritional balance (such as the synergistic effect of protein, fat and unsaturated fatty acids) and the adaptability of reinforcement learning models to different production stages (juvenile stage → adult stage).

[0159] II. Experimental Group Design

[0160] The specific experimental setup and comparative experiments are shown in Table 1:

[0161] Table 1 Experimental Setup and Comparison Experiments

[0162] Experimental group Description of experimental methods Core technical parameters Control group / Experimental group based on Control group (Group A) Traditional artificial formulation + manual parameter adjustment Formula: ω-3=2.5%, ω-6=1.2% Parameters: Temperature 18-22℃, Pressure 0.3-0.5MPa Industry standard operating procedures Experimental Group 1 (Group B) Formula optimization model (linear programming) + traditional manual parameter adjustment Formula: Optimized based on the invention model (target ω-3=3.5%, ω-6=2.0%). Parameters: Same as Group A. Validate formula optimization for independent effects Experimental Group 2 (Group C) Traditional formula + production parameter reinforcement learning adjustment Formula: Same as Group A. Parameters: Real-time adjustment by reinforcement learning model (temperature, pressure, flow rate). Verify the independent effects of parameter optimization. Experimental group 3 (Group D) Formula optimization model + reinforcement learning adjustment of production parameters (complete inventive method) Formula: Same as Group B. Parameters: Real-time adjustment of reinforcement learning model. Systematic advantages of verification methods Additional control group (Group E) Commercial formulation (positive control) Formula: Commercially available high-quality sturgeon feed (ω-3=2.8%, ω-6=1.5%) Parameters: Manufacturer's recommended parameters Comparison of performance of commercially available products

[0163] III. Experimental Setup

[0164] 1. Experimental subjects

[0165] Species: Siberian sturgeon (Acipenser baerii);

[0166] Source: Same batch of juvenile fish from the same hatchery, initial weight (50±5g);

[0167] Aquaculture system:

[0168] Recirculating aquaculture system (flow rate 100L / min, water temperature 18±1℃).

[0169] Aquaculture pond specifications: 3m×2m×1m (effective water volume 5m³);

[0170] Group management:

[0171] Each group has 3 duplicate pools, randomly assigned (15 pools in total, 600 fish).

[0172] Feed four times a day (08:00, 12:00, 16:00, 20:00), with the amount of food being 3% of the body weight.

[0173] 2. Raw materials and production process

[0174] The raw material list is shown in Table 2:

[0175] Table 2 Raw Material List

[0176] Raw material name ω-3 (%) ω-6 (%) protein(%) Fat(%) Moisture (%) Cost (RMB / kg) Deep-sea fish oil 22.5 18.0 0.5 99.0 ≤0.5 15.0 soybean meal 0.8 5.2 45.0 2.0 ≤12.0 3.5 Corn protein powder 0.3 1.2 60.0 0.5 ≤10.0 4.0 Soybean phospholipids 3.0 12.0 1.0 95.0 ≤2.0 8.0 wheat flour 0.2 0.5 12.0 1.5 ≤14.0 2.5

[0177] Production process:

[0178] Raw material pretreatment: crush to 80 mesh (pass rate ≥ 95%);

[0179] Mixing: Horizontal mixer (mixing time 10 minutes, CV ≤ 5%);

[0180] Extrusion: Twin-screw extruder (die diameter 4mm, screw speed 300rpm);

[0181] Drying: Fluidized bed dryer (temperature 80℃, moisture content ≤10%);

[0182] 3. Evaluation Indicators

[0183] Nutritional indicators:

[0184] ω-3 / ω-6 fatty acid content (GB / T 22223-2008 Gas Chromatography);

[0185] Crude protein (Kjeldahl method, GB / T 6432-2018);

[0186] Crude fat (Soxhlet extraction, GB / T 6433-2006);

[0187] Moisture content (105℃ constant weight method, GB / T 6435-2014);

[0188] Production targets:

[0189] Stability of physical parameters: standard deviation (σ) and coefficient of variation (CV) of temperature / pressure / flow rate;

[0190] Production efficiency: energy consumption per ton of material (kW·h / t), output (kg / h);

[0191] Product consistency: feed pellet hardness (N), pulverization rate (%);

[0192] Economic indicators:

[0193] Raw material cost (RMB / kg), energy consumption cost (RMB / t), and comprehensive cost (RMB / kg);

[0194] Sturgeon growth indicators:

[0195] Weight gain rate (WG) = [(final weight - initial weight) / initial weight] × 100%;

[0196] Specific growth rate (SGR) = (ln final weight - ln initial weight) / number of days × 100%;

[0197] Feed conversion ratio (FCR) = Total feed intake / Total weight gain;

[0198] Survival rate (SR) = (Number of fish remaining at the end / Number of fish remaining at the beginning) × 100%;

[0199] IV. Experimental Procedure

[0200] 1. Control group (Group A)

[0201] formula:

[0202] Fish oil 5%, soybean meal 40%, corn gluten meal 30%, phospholipids 3%, wheat flour 22%;

[0203] Theoretical nutritional value: ω-3 = 2.6%, ω-6 = 1.3%, protein = 36.2%;

[0204] parameter:

[0205] Extruder temperature: 18-22℃ (manual adjustment);

[0206] Screw pressure: 0.3-0.5MPa (adjusted manually according to the discharge status);

[0207] 2. Experimental Group 1 (Group B)

[0208] Formula optimization:

[0209] Using the invented linear programming model (juvenile fish stage parameters):

[0210] Optimized results: Fish oil 8%, soybean meal 35%, corn gluten meal 25%, phospholipids 5%, wheat flour 27%;

[0211] Theoretical nutritional value: ω-3=3.4%, ω-6=1.9%, protein=38.5%;

[0212] Parameters: Same as Group A;

[0213] 3. Experimental Group 2 (Group C)

[0214] Formula: Same as Group A;

[0215] Parameter adjustment:

[0216] Reinforcement learning model (Actor-Critic architecture);

[0217] 4. Experimental Group 3 (Group D)

[0218] Formula: Same as the optimized formula in Group B;

[0219] Parameter adjustment: Same as Group C reinforcement learning model;

[0220] 5. Additional control group (Group E)

[0221] Formula: A commercially available brand of sturgeon feed (labeled as ω-3=2.8%, ω-6=1.5%);

[0222] Parameters: As recommended by the manufacturer (temperature 20℃, pressure 0.4MPa).

[0223] V. Data Collection and Analysis

[0224] 1. Data Collection

[0225] Feed analysis:

[0226] Samples are taken every Monday, Wednesday, and Friday (5 particles are taken each time, mixed, and then tested).

[0227] Testing organization: Third-party feed testing center (CMA certified);

[0228] Production monitoring:

[0229] Sensor data: Automatically recorded every 5 minutes (stored in the PLC system);

[0230] Energy consumption data: Real-time monitoring by electricity meter (accuracy 0.1 kW·h).

[0231] Growth performance:

[0232] Weigh yourself every 24 hours after fasting for 10 days (electronic balance, accuracy ±0.1g).

[0233] Feed intake record: the difference between the daily feed amount and the remaining amount (accuracy ±10g).

[0234] 2. Data Analysis

[0235] Statistical tools: SPSS 26.0, GraphPad Prism 9;

[0236] method:

[0237] Normality test: Shapiro-Wilk test;

[0238] Homogeneity of variance test: Levene test;

[0239] Intergroup comparisons: one-way ANOVA + Tukey post-hoc test (p<0.05);

[0240] Correlation analysis: Pearson correlation coefficient (studies the relationship between production parameters and nutritional indicators).

[0241] 3. Quality Control

[0242] Samples of each batch of feed should be retained (stored at 4℃ for 6 months).

[0243] The sensors are calibrated every two weeks (standard thermometer, pressure gauge).

[0244] Training of laboratory personnel: Standardize operating procedures and reduce human error.

[0245] VI. Experimental Data and Conclusions

[0246] The experimental data are shown in Table 3:

[0247] Table 3 Experimental Data

[0248] index Control group (A) Experimental group 1 (B) Experimental group 2 (C) Experimental group 3 (D) Additional control group (E) ω-3 fatty acids (%) 2.6±0.3 3.4±0.2 2.7±0.2 3.7±0.1 2.8±0.1 ω-6 fatty acids (%) 1.3±0.1 1.9±0.1 1.4±0.1 2.1±0.1 1.5±0.1 Temperature standard deviation (°C) 1.2 1.1 0.5 0.4 0.8 Unit cost (yuan / kg) 8.5 8.2 8.4 7.9 9.2 Weight gain rate (%) 120 135 125 140 128 Feed conversion ratio (FCR) 1.8 1.6 1.7 1.5 1.7

[0249] in conclusion:

[0250] 1. Formula optimization (Group B):

[0251] The ω-3 / ω-6 ratio was increased by 30%, but the production stability (temperature σ=1.1℃) was not significantly different from the control group;

[0252] Costs decreased by 3.5% (due to increased fish oil usage but reduced soybean meal usage).

[0253] 2. Parameter Adjustment (Group C):

[0254] The temperature standard deviation decreased by 58% (σ=0.5℃), but nutritional indicators did not improve significantly;

[0255] Energy consumption is reduced by 4% (due to reduced equipment idling caused by parameter optimization).

[0256] 3. Complete inventive method (Group D):

[0257] Significant synergistic effect: the ω-3 / ω-6 ratio reached 3.7% / 2.1%, which was 42% / 61% higher than the control group;

[0258] It has the best production stability (σ temperature = 0.4℃) and the lowest cost (7.9 yuan / kg).

[0259] Sturgeon has the best growth performance (weight gain rate 140%, FCR=1.5).

[0260] The preset parameters or preset thresholds mentioned above are all set by those skilled in the art based on actual conditions or obtained through large-scale data simulation.

[0261] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A method for increasing the proportion of unsaturated fatty acids in a formulated diet for sturgeons, characterized in that, The method comprises the following steps: Step 1: Pre-collecting a raw material information set and a nutritional requirement information set; Step 2: Constructing a formula optimization model based on the raw material information set and the nutritional requirement information set; Step 3: Solving the formula optimization model using an optimization solver to iteratively solve and output an optimized formula result; Step 4: Inputting the optimized formula result into a production process system and monitoring production process monitoring data in real time; Step 5: Constructing a production stability fitness function based on the production process monitoring data; Step 6: Adjusting production parameters using a reinforcement learning model based on the production stability fitness function and the production process monitoring data; The way of monitoring the production process monitoring data in real time is: Using spectral analysis technology to monitor the unsaturated fatty acid content of the mixed raw materials in the production process of the compound feed in real time; Collecting real-time parameter values of various physical parameters in the production process of the compound feed in real time through various physical parameter sensors; The real-time unsaturated fatty acid content and the real-time parameter values of various physical parameters constitute the production process monitoring data; The way of constructing the production stability fitness function based on the production process monitoring data is: Marking the initial moment of producing the compound feed as 0: Marking any moment of producing the compound feed as t; Marking the number of various physical parameters as p; The standard deviation of the pth physical parameter within the 0th moment to the tth moment is marked as ; Constructing the production stability fitness function based on the standard deviation of various physical parameters; The expression of the production stability fitness function G is set as: ; The way of adjusting the production parameters using the reinforcement learning model based on the production stability fitness function and the production process monitoring data is: The reinforcement learning model is set as an Actor-Critic model; Defining the state space, action space and reward function of the reinforcement learning model; The state space includes the content of unsaturated fatty acids and the real-time parameter values of various physical parameters at any t moment in the production process; The action space includes the adjustment amount of all regulated production parameters; The reward function is the weighted sum of the production stability fitness function and the unsaturated fatty acid consumption value, wherein the weight of the unsaturated fatty acid consumption value is negative; The way of solving the formula optimization model using the optimization solver to iteratively solve and output the optimized formula result is: For each growth stage of sturgeon: Using a linear programming solver to solve the formula optimization model corresponding to the growth stage to obtain variable values of the formula proportion variables of various raw materials; The variable values of the formula proportion variables of various raw materials constitute the optimized formula result.

2. The method for increasing the proportion of unsaturated fatty acids in the compound feed of sturgeon according to claim 1, characterized in that, The collection method of the raw material information set is: Analyzing and detecting the nutritional component data and physical and chemical properties of each raw material for making sturgeon compound feed in the laboratory using analytical instruments; Collecting economic parameters of each raw material according to market pricing; The nutritional component data, the physical and chemical properties and the economic parameters constitute the raw material information set.

3. The method for increasing the proportion of unsaturated fatty acids in the compound feed of sturgeon according to claim 2, characterized in that, The collection method of the nutritional requirement information set is: Dividing the growth process of sturgeon into stages to obtain a growth stage list; For each growth stage, the nutritional requirement proportion of each nutritional factor is calculated.

4. The method for increasing the proportion of unsaturated fatty acids in the compound feed of sturgeon according to claim 3, characterized in that, The way of constructing the formula optimization model based on the raw material information set and the nutritional requirement information set is: Mark the number of each growth stage of sturgeon as k; Mark the number of each raw material in the production formula as i, and mark the number of all raw material types as I; Mark the unit content of unsaturated fatty acids in the i-th raw material as UNi; Mark the number of each nutrient element in the nutritional component data except for unsaturated fatty acids as j, and mark the number of all nutrients except for unsaturated fatty acids as J; Mark the unit content of the j-th nutrient element in the i-th raw material as Nij; Set the preset target proportion of unsaturated fatty acids for the k-th growth stage as UTk; Set the preset target proportion of the j-th nutrient element for the k-th growth stage as Tkj; Mark the unit cost of the i-th raw material as Ci, and mark the cost budget of the unit amount of the compound feed as Cmax; Set the formula proportion variable xki for the i-th raw material in the k-th growth stage; Set the minimum requirement content UDk of unsaturated fatty acids and the minimum requirement content Dkj of the j-th nutrient element for the k-th growth stage; For the k-th growth stage: Based on the unit content of unsaturated fatty acids, the unit content of nutrient elements, the preset target proportion of unsaturated fatty acids, the preset target proportion of nutrient elements, and the formula proportion variable, a formula target function is constructed; The formula of the formula target function Fk is set as: ; wherein w0 and wj are both preset proportion coefficients; Based on the formula proportion variable, the minimum requirement content of unsaturated fatty acids and the j-th nutrient element, the unit cost of each raw material, and the cost budget, a constraint condition set is constructed; The constraint condition set is constructed in the following manner: Mark the constraint condition set of the k-th growth stage as Uk; The constraint conditions contained in Uk include: ; the constraint is that the unit content of unsaturated fatty acids must not be lower than the minimum required content; ; the constraint is that the total content of any jthnutrient element cannot be lower than the minimum required content corresponding to the jthnutrient element; ; the constraint is that the sum of the proportions of all raw materials should be 1; ; cost constraints on the quantity of the compound feed; A linear programming model constructed with the optimization goal of maximizing the formula target function and the constraint condition set as the constraint is used as the formula optimization model.

5. The method for increasing the proportion of unsaturated fatty acids in the compound feed for sturgeons according to claim 4, characterized in that, The input of the optimization formula result into the production process system is: According to the growth stage of the sturgeon to be fed, the formula proportion variable of each raw material in the optimization formula result corresponding to the growth stage is used to proportion the raw materials, and the production raw materials of the mixed compound feed are obtained.

6. The method for increasing the proportion of unsaturated fatty acids in the compound feed of sturgeon according to claim 5, characterized in that: Further comprising: Initializing the model parameters of the Actor network and the Critic network, and setting the optimizer as the Adam optimizer; At each time t: The current state is obtained from the environment, the Actor network is used to select the action, and the selected action is executed to observe the state at the next time, and the reward value is calculated, and the experience is stored in the experience replay buffer, the experience including the current state, the selected action, the state at the next time and the reward value; A batch of experiences are randomly sampled from the experience replay buffer, and the target Q value is calculated; The mean square error function is used as the loss function of the Critic network model, and the soft update strategy is used to update the parameters of the Critic network; Through multiple iterations of updating, the production parameters are optimized to maximize the reward function.

7. A computer-readable storage medium, characterized in that, The computer program is stored thereon; When the computer program runs on the computer device, the computer device executes the method for improving the proportion of unsaturated fatty acids in the compound feed of sturgeon in the background. 1-6.

Images