Formula of soybean-meal-free daily ration feed for fattening ruminants and preparation method of soybean-meal-free daily ration feed

Abstract

The invention provides a formula technology preparation method of a ruminant fattening soybean-meal-free daily ration feed which comprises the following components in percentage by mass: 30-40% of corn, 8-12% of wheat bran, 10-15% of corn distillers' grains, 8-12% of cottonseed meal, 5-10% of rapeseed meal, 3-5% of fish meal, 3-6% of corn protein powder, 5-8% of fermented bean dregs, 6-10% of microbial fermented straw, 2-4% of yeast culture and 1.5-2.5% of mineral element premix. 1-2% of a vitamin premix, 0.3-0.7% of a compound enzyme preparation and 0.5-1% of a microecological preparation. In the traditional feed granulation process, moisture, temperature and pressure are unstable, so that particles are uneven in hardness, large in dust amount and prone to mildewing. According to the method, the optimal granulation parameters are calculated by adopting MOPSO, and the particle uniformity and the storage stability are improved. The intelligent granulation optimization improves the water resistance of particles, reduces crushed materials, improves the palatability of the feed, reduces dust, prolongs the shelf life of the feed, and reduces the storage loss.

Description

Technical Field

[0001] The present invention relates to the technical field of feeds, and specifically to a formula for a soybean-meal-free diet feed for fattening ruminants and a preparation method thereof. Background Art

[0002] During the fattening process of ruminants (such as cattle and sheep), traditional diet formulas mainly rely on soybean meal as the protein source. However, soybean meal has problems such as large price fluctuations, limited supply, and anti-nutritional factors affecting digestion and absorption, resulting in high feed costs and limited fattening efficiency. In addition, ruminants have limited digestive ability for crude fiber, the fiber components in traditional feeds are not fully utilized, and alternative proteins (such as cottonseed meal, rapeseed meal, fermented soybean residue) are not finely proportioned and optimized, which easily causes protein imbalance and affects the fattening effect.

[0003] In recent years, with the application of intelligent optimization algorithms (such as multi-objective particle swarm optimization MOPSO) and artificial intelligence (AI) in feed formula optimization, researchers have tried to use alternative protein sources (such as cottonseed meal, rapeseed meal, fermented soybean residue, etc.), combined with microbial fermentation and enzymatic hydrolysis technologies, to improve the protein digestibility, fiber degradation rate, fattening efficiency, and storage stability of feeds. However, there is no good application method. The existing microbial fermentation technology lacks precise regulation, the straw degradation efficiency is unstable, affecting feed nutrient absorption. The existing process mainly relies on fixed temperature or manual regulation, lacking an intelligent regulation mechanism and being difficult to dynamically optimize the enzymatic hydrolysis efficiency. The existing granulation process fails to achieve intelligent optimization, easily resulting in a high feed dust rate, poor storage stability, and a high risk of mildew. Summary of the Invention

[0004] The purpose of the present invention is to provide a formula for a soybean-meal-free diet feed for fattening ruminants and a preparation method thereof. By adopting a soybean-meal-free formula, the cost is reduced and the fattening efficiency is improved. With AI intelligent optimization (MOPSO + LSTM + neural network), precise feed proportioning, intelligent temperature control, and dynamic enzyme activity optimization are achieved, the fiber degradation rate is increased, the feed energy utilization is optimized, the granulation process is optimized, and the quality and storage stability of feed pellets are improved. The present invention breaks through the bottleneck of traditional fattening feeds, provides a more economical, efficient, and environmentally friendly soybean-meal-free diet feed for ruminants, and has broad industrial application value.

[0005] To achieve the above object, the present invention proposes the following technical solution: A formula for a soybean-meal-free diet feed for fattening ruminants, and the formula composition is as follows by mass percentage:

[0006] 30 - 40% corn, 8 - 12% wheat bran, 10 - 15% corn distillers grains, 8 - 12% cottonseed meal, 5 - 10% rapeseed meal, 3 - 5% fish meal, 3 - 6% corn gluten meal, 5 - 8% fermented soybean residue, 6 - 10% microbially fermented straw, 2 - 4% yeast culture, 1.5 - 2.5% mineral element premix, 1 - 2% vitamin premix, 0.3 - 0.7% compound enzyme preparation, 0.5 - 1% microecological preparation.

[0007] Furthermore, in the present invention, the microecological preparation is lactic acid bacteria or bacillus.

[0008] Furthermore, in the present invention, the yeast culture includes β-glucan, mannan, yeast protein, lactic acid, active yeast strains, nucleotides, and B vitamins;

[0009] β-glucan promotes immunity and improves disease resistance. Yeast protein provides high-quality amino acids and improves feed protein utilization rate. Lactic acid stabilizes rumen pH and improves feed digestibility. Active yeast strains (Saccharomyces cerevisiae) improve rumen microbial activity and promote fiber degradation. Nucleotides promote intestinal development and improve nutrient absorption. B vitamins promote energy metabolism and reduce digestive stress.

[0010] The function of the yeast culture is to promote rumen fermentation, enhance the digestion ability of ruminants for crude fiber and protein, optimize the rumen microflora, improve feed utilization rate, reduce diarrhea and intestinal diseases, increase daily weight gain and feed conversion rate, and shorten the fattening cycle.

[0011] The mineral element premix is used to supplement the essential minerals required for the growth of ruminants, and it includes the following components: calcium carbonate, calcium dihydrogen phosphate, magnesium oxide, sodium chloride, potassium chloride, sodium sulfate, zinc oxide, copper methionine, ferrous sulfate, manganese methionine, selenium yeast, and calcium iodate;

[0012] Calcium carbonate promotes bone development and improves muscle growth. Calcium dihydrogen phosphate promotes energy metabolism and DNA synthesis. Magnesium oxide participates in enzymatic reactions and maintains nerve and muscle functions. Sodium chloride maintains fluid balance and promotes gastric acid secretion. Potassium chloride maintains cell osmotic pressure and improves heat tolerance. Sodium sulfate promotes the synthesis of amino acids by ruminant microorganisms. Zinc oxide promotes immune function and increases growth rate. Copper methionine promotes iron absorption and improves fur quality. Ferrous sulfate prevents anemia and improves oxygen transport ability. Manganese methionine promotes bone development and improves reproductive performance. Selenium yeast has antioxidant properties and improves immunity. Calcium iodate maintains thyroid function and promotes metabolism.

[0013] Mineral element premix supplements essential minerals, optimizes bone development, and enhances immunity. It improves the rumen microbial fermentation environment, promotes digestion and absorption, and increases feed conversion rate. It enhances antioxidant capacity, reduces oxidative stress, and improves growth performance.

[0014] The vitamin premix includes vitamin A, vitamin D 3 , vitamin E, vitamin K 3 , vitamin B 1 , vitamin B 2 , vitamin B 6 , niacin, pantothenic acid, folic acid, biotin, and vitamin B 12 .

[0015] Vitamin A maintains vision, enhances immunity, and promotes bone development. Vitamin D 3 promotes calcium and phosphorus absorption and strengthens bone strength. Vitamin E has antioxidant properties, reduces oxidative stress, and improves reproductive ability. Vitamin K 3 promotes blood coagulation and reduces hemorrhagic diseases. Vitamin B 1 participates in carbohydrate metabolism and maintains nerve function. Vitamin B 2 promotes cell metabolism and increases feed utilization rate. Vitamin B 6 participates in protein metabolism and improves immune function. Niacin participates in energy metabolism and increases growth rate. Pantothenic acid promotes protein synthesis and increases feed utilization rate. Folic acid promotes blood synthesis and improves reproductive rate. Biotin maintains skin health and improves feed palatability. Vitamin B 12 promotes DNA synthesis and increases red blood cell production.

[0016] The vitamin premix increases the growth rate of ruminants, optimizes the growth and metabolic pathways. It reduces oxidative stress, increases feed conversion rate and reproductive ability. It enhances the immune system, reduces diseases, and improves production performance.

[0017] A method for preparing a soybean meal-free diet feed for fattening ruminants includes the following steps:

[0018] Step 1, raw material selection and pretreatment. The raw materials are selected, and the optimal raw material ratio is calculated using MOPSO with cost, protein content, and metabolic energy as the optimization objectives. The pretreatment includes detoxification treatment and preparation of fermented soybean residue.

[0019] Step 2, preparation of microbially fermented straw. The degradation progress of corn straw is predicted using LSTM to optimize the enzymatic hydrolysis efficiency.

[0020] Step 3: Pretreatment with a compound enzyme preparation. The optimal activation conditions of the enzyme activity are predicted by neural network. The compound enzyme preparation includes xylanase, cellulase, and β-glucanase. The compound enzyme preparation is mixed with water at a ratio of 1:10, and the temperature is regulated by AI.

[0021] Step 4: Feed mixing and granulation. First, mix corn, wheat bran, and DDGS; then add cottonseed meal, rapeseed meal, fish meal, corn protein powder, fermented soybean residue, and microbial fermented straw; finally, add mineral element premix, vitamin premix, compound enzyme preparation, and microecological preparation. Use a ring die granulator, optimize the temperature control, and adjust the moisture by AI; control the particle size and optimize the feed uniformity; use AI to adjust the compression force to reduce the broken material rate; cool by air cooling, and seal and package after reaching room temperature.

[0022] Further, in the present invention, in the said Step 1, when selecting raw materials, use MOPSO to calculate the optimal raw material ratio:

[0023]

[0024] F(X): Optimization objective function, the smaller the better;

[0025] C(X): Feed cost (yuan / kg), optimize cost control;

[0026] P(X): Crude protein content of feed (%), ensure nutritional balance;

[0027] E(X): Metabolizable energy (MJ / kg), improve digestibility;

[0028] ω 1 ,ω 2 ,ω 3 : Weight factor, adaptively adjusted by neural network;

[0029] P opt : Target crude protein content;

[0030] E opt : Target metabolizable energy;

[0031] Multi-objective particle swarm optimization (MOPSO): When optimizing the feed ratio, it is necessary to balance among cost, protein content, and metabolizable energy. MOPSO finds the optimal ratio through intelligent search. Neural network adaptively adjusts the weights: Dynamically adjust the priority of each parameter according to the market price fluctuation of feed and breeding requirements. Intelligent formula optimization reduces manual adjustment, improves feed economy and nutritional balance. Automatically adapt to market price fluctuations, reduce production costs, and increase profit margins.

[0032] Select the following raw materials: corn, wheat bran, DDGS, cottonseed meal, rapeseed meal, fish meal, corn protein powder, fermented soybean residue, and microbial fermented straw;

[0033] Detoxification treatment: Free gossypol and glucosinolate in cottonseed meal and rapeseed meal need to be removed to reduce toxic and side effects;

[0034] Intelligent temperature control for preparing fermented soybean residue: Adjust the moisture to 60%;

[0035] AI Optimized Temperature Control:

[0036] T(t + 1) = T(t) + k 1 (T opt - T(t)) + k 2 ∑e t + k 3 (e t - e t-1 );

[0037] T(t + 1): Temperature at the (t + 1)-th moment;

[0038] T(t): Temperature at the t-th moment;

[0039] T opt : Optimal fermentation temperature;

[0040] k 1 , k 2 , k 3 : Temperature adjustment coefficient;

[0041] e t = T opt - T(t): Temperature deviation;

[0042] e t-1 : Temperature deviation at the previous moment;

[0043] Inoculate lactic acid bacteria, yeast, and Bacillus subtilis, 10 7 CFU per gram; Ferment in a closed state for 48 h, and the AI dynamically adjusts the temperature to increase the protein solubility. Optimize the temperature based on PID (Proportional-Integral-Derivative) control to prevent excessive temperature fluctuations during fermentation from affecting the microbial activity. The AI predicts the optimal temperature, uses a neural network to calculate the temperature adjustment strategy in real time, and optimizes the fermentation effect. Stabilize the fermentation temperature, increase the protein solubility, and enhance the feed digestibility. Intelligent dynamic regulation ensures the best microbial fermentation environment and improves the nutritional value.

[0044] Furthermore, in the present invention, in step 2, an LSTM (Long Short-Term Memory Neural Network) is used to predict the degradation progress and optimize the enzymatic hydrolysis efficiency:

[0045]

[0046] E dose ( t ): Enzyme dosage at the t-th moment;

[0047] S(t): Undegraded cellulose content;

[0048] t opt : Optimal enzymatic hydrolysis time;

[0049] α is the reaction rate coefficient determined by PSO;

[0050] For the specific operation, take corn straw and crush it to a particle size of 3 - 5 mm; adjust the moisture content to 60%, add 3% corn syrup or glucose as the carbon source; inoculate with a mixed strain of actinomycetes, Aspergillus niger, and lactic acid bacteria, with a dosage of 10 8 CFU / g; AI controls the temperature and humidity, dynamically regulates the enzyme dosage, and ferments for 72 h.

[0051] Use LSTM to predict the progress of straw degradation, train the AI model in combination with experimental data, and predict the optimal enzyme dosage. Optimize the enzyme dosage strategy based on the Logistic function to ensure that the enzyme dosage can efficiently degrade cellulose without causing waste. Improve the straw degradation rate and optimize the utilization rate of feed fiber. Intelligent enzyme dosage reduces the cost of enzyme preparations.

[0052] Furthermore, in the present invention, in step 3, the neural network predicts the best activation conditions of enzyme activity:

[0053]

[0054] T opt : The best activation temperature; T initial : The initial temperature; γsin(ωt): Compensate for environmental fluctuations;

[0055] When AI regulates the temperature, the initial temperature is 30 °C, and it is gradually adjusted to the optimal temperature; activate for 2 h, stir evenly to improve the enzyme activity. Use AI to predict temperature changes and adjust the enzyme activation temperature to ensure the highest enzyme activity. Dynamic temperature compensation prevents the environmental temperature fluctuation from affecting the activity of the enzyme preparation. Improve the enzyme activity, enhance the degradation efficiency, and improve the protein utilization rate. Avoid enzyme inactivation caused by temperature changes and improve the feed stability.

[0056] Furthermore, in the present invention, in step 4, an intelligent granulation optimization formula is adopted to optimize the uniformity and mechanical stability of feed granulation:

[0057]

[0058] P opt : The optimal granulation parameters; U(P): The granule uniformity score, the higher the better, L(P): The granulation loss, the smaller the better; k 6 , k 7 : The optimization weight coefficient. AI calculates the best granulation temperature, pressure, and moisture content to optimize the granule quality and storage stability. MOPSO selects the best granulation parameters to balance the granule strength and palatability. Improve the feed granulation uniformity, reduce dust, and improve palatability. Optimize the storage stability, reduce the feed mildew rate, and improve the water resistance.

[0059] The optimization method uses AI + optimization algorithms to improve the nutritional value, digestibility, conversion rate, and storage stability of feed, and can be widely applied to ruminant farming to improve farming efficiency and feed utilization rate.

[0060] Beneficial effects: The technical solution of this application has the following technical effects:

[0061] 1. The soybean meal-free formula improves the economy of feed, replaces proteins (such as cottonseed meal, rapeseed meal, fermented soybean dregs, etc.), reduces the dependence on soybean meal, reduces the impact of protein raw material fluctuations on feed costs, improves protein utilization rate, and enhances the fattening effect.

[0062] Traditional feed relies on soybean meal to provide protein, but the price of soybean meal fluctuates greatly, and it contains anti-nutritional factors (such as trypsin inhibitors), which affect protein digestibility. This invention uses various alternative protein sources such as cottonseed meal, rapeseed meal, fermented soybean dregs, and corn protein powder, and through AI formula optimization (MOPSO), ensures balanced and easily digestible protein. MOPSO intelligently optimizes the protein content, improves feed utilization rate, dynamically adapts to market changes, and reduces production costs.

[0063] 2. AI intelligent optimization of the formula improves the nutritional balance of feed. Based on MOPSO (Multi-Objective Particle Swarm Optimization), the optimal formula is calculated, taking into account protein, metabolic energy, and cost, dynamically adjusting the proportion of raw materials, adapting to market price fluctuations, increasing farming profits, improving feed conversion rate, and reducing waste.

[0064] 3. Improve the digestibility of crude fiber and optimize energy utilization. Microbial fermentation of straw (actinomycetes, Aspergillus niger, lactic acid bacteria) degrades lignin, improves fiber digestibility, and LSTM (Long Short-Term Memory Neural Network) optimizes the straw degradation process to improve energy conversion rate.

[0065] Traditional straw has a high lignin content and is difficult for ruminants to digest, resulting in feed waste. This invention uses LSTM to predict the straw degradation process and combines it with microbial fermentation to improve the fiber degradation rate. LSTM predicts the enzymatic hydrolysis efficiency and dynamically adjusts the enzyme dosage to ensure the best degradation effect, improve fiber digestibility, and optimize energy utilization.

[0066] 4. Intelligent enzymatic hydrolysis improves the degradation rate of protein and fiber. AI controls the enzyme activity temperature, improves the degradation efficiency, reduces enzyme inactivation, reduces anti-nutritional factors, and improves feed palatability.

[0067] Complex enzymes (xylanase, cellulase, β-glucanase) need to be activated at an appropriate temperature. Traditional methods are difficult to precisely control the temperature, resulting in low enzyme activity and low degradation efficiency. This invention uses neural networks to optimize temperature control, ensures the optimal enzyme activity temperature, and improves feed digestibility. Intelligently adjusts the temperature to prevent enzyme inactivation, increases the protein degradation rate, reduces protein waste, and improves feed palatability.

[0068] 5. Optimize the granulation process to improve storage stability. AI optimizes granulation temperature, pressure, and moisture to improve pellet quality, water resistance, reduce dust, enhance feed palatability, lower feed mold rate, and extend the shelf life.

[0069] During the traditional feed granulation process, the instability of moisture, temperature, and pressure results in uneven pellet hardness, high dust content, and easy mildew. This invention uses MOPSO to calculate the optimal granulation parameters to improve pellet uniformity and storage stability. Intelligent granulation optimization enhances pellet water resistance, reduces broken materials, improves feed palatability, decreases dust, extends the feed shelf life, and reduces storage losses.

[0070] It should be understood that all combinations of the foregoing concepts and additional concepts described in greater detail below can be regarded as part of the inventive subject matter of the present disclosure as long as such concepts do not conflict with each other.

[0071] The foregoing and other aspects, embodiments, and features of the teachings of the present invention can be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the present invention, such as the features and / or beneficial effects of exemplary embodiments, will be apparent in the following description or will be learned through practice of the specific embodiments according to the teachings of the present invention. Brief Description of the Drawings

[0072] The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component shown in various figures may be represented by the same reference numeral. For clarity, not every component is labeled in each figure. Now, embodiments of various aspects of the present invention will be described by way of example and with reference to the drawings, where:

[0073] Figure 1 It is a schematic structural diagram of the present invention. Detailed Description of the Embodiments

[0074] To better understand the technical content of the present invention, specific embodiments are hereby given and described in conjunction with the accompanying drawings as follows. In the present disclosure, aspects of the present invention are described with reference to the drawings, and many illustrative embodiments are shown in the drawings. The embodiments of the present disclosure do not necessarily define all aspects of the present invention. It should be understood that the various concepts and embodiments introduced above, as well as those concepts and embodiments described in greater detail below, can be implemented in any of many ways because the concepts and embodiments disclosed in the present invention are not limited to any embodiment. Additionally, some aspects of the present invention can be used alone or in any suitable combination with other aspects of the present invention.

[0075] The embodiment provides a formula and preparation method for a soybean - meal - free diet feed for fattening ruminants. The formula composition is as follows by mass percentage:

[0076] 30 - 40% corn, 8 - 12% wheat bran, 10 - 15% corn distillers grains, 8 - 12% cottonseed meal, 5 - 10% rapeseed meal, 3 - 5% fish meal, 3 - 6% corn gluten meal, 5 - 8% fermented soybean residue, 6 - 10% microbial fermented straw, 2 - 4% yeast culture, 1.5 - 2.5% mineral element premix, 1 - 2% vitamin premix, 0.3 - 0.7% compound enzyme preparation, 0.5 - 1% microecological preparation.

[0077] Among them, the microecological preparation is lactic acid bacteria or bacillus.

[0078] Among them, the yeast culture includes β - glucan, mannan, yeast protein, lactic acid, active yeast strains, nucleotides, vitamin B group;

[0079] The mineral element premix is used to supplement the essential minerals required for the growth of ruminants, and it includes the following components: calcium carbonate, calcium dihydrogen phosphate, magnesium oxide, sodium chloride, potassium chloride, sodium sulfate, zinc oxide, copper methionine, ferrous sulfate, manganese methionine, selenium yeast and calcium iodate;

[0080] The vitamin premix includes vitamin A, vitamin D3, vitamin E, vitamin K3, vitamin B1, vitamin B2, vitamin B6, nicotinic acid, pantothenic acid, folic acid, biotin and vitamin B12

[0081] The preparation method of the soybean - meal - free diet for fattening ruminants is as follows:

[0082] Raw material selection and pretreatment: Select raw materials such as corn, wheat bran, corn distillers grains (DDGS), cottonseed meal, rapeseed meal, fish meal, corn gluten meal, fermented soybean residue, microbial fermented straw, etc. Cottonseed meal and rapeseed meal need to be detoxified to remove free gossypol and glucosinolates to reduce toxicity. Use the MOPSO optimization algorithm to calculate the optimal raw material ratio, with feed cost, protein content and metabolic energy as the optimization objectives.

[0083] Specifically, use a crusher to crush corn and straw to 3 - 5 mm to improve the feed mixing uniformity. Use a solvent extraction device or heating method to remove the antinutritional factors in cottonseed meal and rapeseed meal. Use an automatic humidification system to adjust the humidity of raw materials such as fermented soybean residue and straw to 60%.

[0084] Preparation of microbial fermented straw: Select corn straw and crush it to 3 - 5 mm. Add 3% corn syrup or glucose as a carbon source. Inoculate actinomycetes, Aspergillus niger, and lactic acid bacteria, with an inoculation amount of 10 8 CFU / g.

[0085] Fermentation control: The fermentation equipment uses a fermenter with temperature and humidity monitoring. The intelligent temperature control adopts an AI-optimized LSTM prediction model to dynamically adjust the fermentation temperature (35 - 40 °C), and the humidity is maintained at 60%. PID control is used to ensure that the temperature fluctuation is less than ±1 °C. The fermentation time is 72 hours under airtight conditions at the optimal temperature and humidity conditions to improve the lignin degradation rate.

[0086] Pretreatment with compound enzyme preparation: The neural network algorithm is used to predict the optimal enzyme activity temperature for enzyme activation. In a constant temperature water bath stirrer, xylanase, cellulase, and β-glucanase are dissolved in water at a ratio of 1:10, the temperature is adjusted to 30 - 35 °C, and activation is carried out for 2 hours. AI automatically adjusts the stirring rate to ensure uniform dissolution and improve enzyme activity.

[0087] Feed mixing and granulation: A high-speed mixer is used for mixing in the following order: corn, wheat bran, corn distillers grains with solubles (DDGS); cottonseed meal, rapeseed meal, fish meal, corn protein powder, fermented soybean residue, and microbial fermented straw are added; finally, mineral element premix, vitamin premix, compound enzyme preparation, and microecological preparation are added.

[0088] Granulation is carried out using a ring die granulator. AI optimizes the temperature, pressure, and moisture to improve the pellet quality. Granulation parameter optimization: Granulation temperature: 70 - 80 °C. Moisture control: 12 - 14%. AI is used to adjust the compression force to ensure pellet uniformity and reduce dust. After granulation of the pellet feed, an air-cooling system is used to cool it to room temperature to reduce caking and improve storage stability.

[0089] In quality inspection, the Kjeldahl nitrogen analyzer is used to determine the crude protein content of the feed to ensure compliance with the design requirements. The bomb calorimeter is used to determine the metabolic energy to optimize the feed energy supply. The water resistance tester is used to detect the water resistance of the feed pellets to improve palatability. The dust measuring equipment is used to detect the dust content during the granulation process to reduce waste and pollution.

[0090] Through feeding trials, the feed digestibility and the crude fiber degradation rate in feces are measured to verify the formula effect.

[0091] It is sealed with a moisture-proof packaging bag to prevent the feed from absorbing moisture and deteriorating.

[0092] Specific experiments are as follows in the following examples:

[0093] Example 1: Effect of the optimized soybean meal-free diet feed on the growth performance of fattening cattle

[0094] 1. Experimental design

[0095] Experimental animals: Select 60 fattening cattle with a weight of 200 ± 5 kg and randomly divide them into two groups:

[0096] Control group (traditional soybean meal-containing feed): Use a conventional soybean meal-containing diet formula.

[0097] Experimental group (soybean meal-free diet feed of the present invention): The optimized soybean meal-free diet feed is adopted.

[0098] Test cycle: 120 days.

[0099] Test conditions: Free access to food and water, and the feeding environment is kept consistent.

[0100] 2. The feed formula is as follows (mass percentage)

[0101] Ingredient Control Group (%) Experimental Group (%) Corn 40 38 Wheat Bran 10 10 DOGS 10 12 Soybean Meal 12 0 Cottonseed Meal 0 10 Rapeseed Meal O 8 Fish Meal 4 4 Corn Gluten Meal 3 5 Fermented Okara 0 6 Microbial Fermented Straw 0 7 Yeast Culture 0 3 Mineral Element Premix 2 22 Vitamin Premix 2 22 Compound Enzyme Preparation 0 0.5 Microecological Preparation 0 1 Total 100 100

[0102] 3. Test process and determination method

[0103] Body weight measurement: The individual body weight is measured before the start of the test and every 30 days.

[0104] Feed intake: The feed intake is recorded daily, and the total feed intake is calculated.

[0105] Blood biochemical index determination: Blood samples are collected at the start and end of the test, and biochemical indexes such as total protein (TP), albumin (ALB), blood urea nitrogen (BUN), and blood glucose (GLU) are analyzed.

[0106] Fecal analysis: Fecal samples are collected to measure the digestibility and the degradation rate of crude fiber in feces.

[0107] 4. Test results

[0108]

[0109] The conclusions are as follows: The daily weight gain increases by 11.3%, indicating that the optimized formula can more effectively promote the growth of fattening cattle. The feed conversion rate increases by 9.6%, indicating that the feed in the experimental group has a higher nutritional utilization rate. The fattening cycle is shortened by 8.3%, meaning that the breeding cost is reduced and the economic benefit is improved. The serum total protein increases by 6.9%, indicating that the protein metabolism is improved and the nutrient absorption is better. The degradation rate of fecal crude fiber increases by 14.8%, indicating that the fiber digestibility is significantly improved and the energy utilization is increased.

[0110] Example 2: Influence of intelligent temperature control optimization on the quality of fermented okara

[0111] 1. Test purpose

[0112] This test aims to verify the role of the AI intelligent temperature control system in the production of fermented okara and evaluate its influence on indexes such as protein solubility, the number of lactic acid bacteria, and the degradation rate of anti-nutritional factors.

[0113] 2. Test design

[0114] Test materials:

[0115] Raw materials: wet soybean dregs (water content 75%), Lactobacillus, Saccharomyces cerevisiae, Bacillus subtilis.

[0116] Equipment: AI intelligent temperature-controlled fermentation tank (with real-time temperature and humidity monitoring), gas chromatograph (for detecting organic acid content), Kjeldahl nitrogen analyzer (for measuring protein solubility).

[0117] Experimental groups:

[0118] Control group (fixed temperature): Traditional fermentation at a fixed temperature of 35°C.

[0119] Experimental group (AI temperature control optimization): The temperature is adjusted by AI within the range of 32 - 38°C and dynamically adjusted according to the growth state of microorganisms.

[0120] Fermentation process:

[0121] The water content of wet soybean dregs is adjusted to 60%.

[0122] According to an inoculum size of 10 7 CFU / g, the mixed strains (Lactobacillus, Saccharomyces cerevisiae, Bacillus subtilis) are added.

[0123] Ferment for 48 hours under airtight conditions. Implement AI temperature control for the experimental group and dynamically monitor parameters such as temperature, pH, and dissolved oxygen.

[0124] After fermentation, samples are taken for detecting protein solubility, the number of Lactobacillus, and the degradation rate of anti-nutritional factors.

[0125] 3. Measurement methods

[0126] Detection Index Determination Method Protein Solubility (%) Kjeldahl Method (Determination of Soluble Protein Nitrogen Content) Lactic Acid Bacteria Count (CFU / g) Plate Counting Method Antinutritional Factor Degradation Rate (%) High Performance Liquid Chromatography (HPLC), Determination of Trypsin Inhibitor and Phytate Degradation Rate

[0127] 4. Data analysis of the experiment

[0128] Index Control Group (Fixed Temperature 35°C) Experimental Group (AI Temperature Control 32 - 38°C) Change Rate (%) Protein Solubility (%) 65.2 72.5 +11.2％ Lactic Acid Bacteria Count (CFU / g) <![CDATA[5.2×10 7 > <![CDATA[6.8×10 7 > +308％ Antinutritional Factor Degradation Rate (%) 42.3 55.7 +31.7％

[0129] Result analysis: The protein solubility increased by 11.2%, indicating that AI intelligent temperature control helps to enhance the decomposition of proteins during fermentation and improve the content of available proteins. The number of Lactobacillus increased by 30.8%, indicating that AI temperature control maintains a more stable microbial growth environment, helps the proliferation of Lactobacillus, improves the palatability of feed and the health of animal intestines. The degradation rate of anti-nutritional factors increased by 31.7%, indicating that AI temperature control helps to improve the degradation of anti-nutritional factors during fermentation, such as trypsin inhibitors, phytic acid, etc., and improves feed digestibility.

[0130] This experiment shows that the AI intelligent temperature control system can dynamically adjust the temperature, improve the protein solubility, the number of lactic acid bacteria, and the degradation rate of anti-nutritional factors in fermented soybean dregs, thereby optimizing the digestibility and palatability of the feed.

[0131] Example 3: Influence of Intelligent Pelleting Optimization on the Quality of Pelleted Feed

[0132] 1. Test Purpose

[0133] This experiment verifies the influence of the AI pelleting optimization system on the quality of feed pellets and evaluates its improvement effect on key parameters such as pellet uniformity, water resistance, and dust rate.

[0134] 2. Test Design

[0135] Test Materials:

[0136] Raw Materials: Optimized soybean meal-free diet feed.

[0137] Equipment: Ring die pellet mill (equipped with AI temperature and humidity regulation system), dust collector, water resistance tester.

[0138] Test Groups:

[0139] Control Group (Fixed Temperature): Pelleting at a constant temperature of 75°C.

[0140] Test Group (AI Pelleting Optimization): AI regulates the pelleting temperature from 70 to 80°C and dynamically adjusts the pressure and moisture content.

[0141] Pelleting Process:

[0142] Adjust the feed moisture to 12 - 14%.

[0143] Use a ring die pellet mill for pelleting. For the test group, use an AI temperature and humidity monitoring system to real-time regulate the pelleting parameters.

[0144] After pelleting, perform air cooling to reduce the temperature, and take samples to detect the pellet quality indicators.

[0145] 3. Measurement Methods

[0146] Detection Index Determination Method Particle Uniformity (%) Image Analysis System, Determination of Particle Diameter Distribution Water Resistance (min) Water Bath Immersion Method (Time Required for Complete Disintegration of Particles) Dust Rate (%) Mechanical Vibration Sieve Method

[0147] 4. Test Data Analysis

[0148] Index Control Group (Pelleting at 75°C Constant Temperature) Experimental Group (AI Pelleting Optimization 70 - 80°C) Change Rate (%) Particle Uniformity (%) 85.2 92.7 +8.8％ Water Resistance (min) 30 38 +26.7％ Dust Rate (%) 8.5 6.2 -27.1％

[0149] Result analysis shows that the particle uniformity has increased by 8.8%, indicating that AI optimized the control of granulation temperature and pressure, improving the particle morphology consistency and reducing feed debris. The water resistance has increased by 26.7%, suggesting that AI dynamic regulation has enhanced the stability of feed particles, making them more resistant to digestion in the rumen environment of ruminants. The dust rate has decreased by 27.1%, indicating that AI granulation optimization has reduced the fine powder content, improved feed palatability, and increased feed utilization rate.

[0150] This experiment shows that the AI granulation optimization technology improves the uniformity and water resistance of feed particles by dynamically adjusting granulation temperature, pressure, and moisture, while reducing the dust rate, thereby improving feed quality and storage stability.

[0151] Intelligent temperature control optimization: increases the solubility of fermented okara protein (+11.2%), reduces anti-nutritional factors (-31.7%), and enhances feed digestibility. Intelligent granulation optimization: improves particle uniformity (+8.8%), enhances water resistance (+26.7%), reduces dust (-27.1%), and optimizes storage stability. Intelligent technology improves feed quality and breeding efficiency, and is applicable to large-scale feed production and breeding.

[0152] Example 4

[0153] The experimental data verifies its innovation and advantages in terms of nutritional value, fattening effect, feed conversion rate, and cost control.

[0154] 1. Formula composition (by mass percentage)

[0155] Raw Material Name Control Group (Containing Soybean Meal) % Experimental Group (Without Soybean Meal) % Corn 45 48 DDGS (Corn Distillers Grains) 10 12 Wheat Bran 8 10 Cottonseed Meal 6 0 Rapeseed Meal 5 0 Soybean Meal 12 0 Fermented Okara 0 10 Fish Meal 3 4 Corn Gluten Meal 4 5 Microbial Fermented Straw 0 6 Mineral Element Premix 2 2 Vitamin Premix 2 2 Compound Enzyme Preparation 1 1 Microecological Preparation 2 2 Total 100 100

[0156] 2. Specific preparation method

[0157] Step 1: Raw material selection and pretreatment

[0158] Raw material selection

[0159] Select fresh and non-moldy raw materials such as corn, wheat bran, DDGS, fish meal, corn protein powder, fermented okara, and microbial fermented straw.

[0160] Cottonseed meal and rapeseed meal are not used in the soybean meal-free diet due to the presence of anti-nutritional factors.

[0161] Preparation of fermented okara

[0162] Adjust the wet okara to 60% moisture.

[0163] Inoculate with a mixed strain of lactic acid bacteria, yeast, Bacillus subtilis, etc. (10 7 CFU per gram).

[0164] Ferment in a closed container at 35°C for 48 hours to reduce anti-nutritional factors and increase the proportion of soluble protein.

[0165] Preparation of straw by microbial fermentation

[0166] Take corn straw and crush it to a particle size of 3 - 5 mm.

[0167] Adjust the moisture to 60% and add 3% corn syrup or glucose as a carbon source.

[0168] Inoculate with a mixed strain of actinomycetes, Aspergillus niger, and lactic acid bacteria (10 8 CFU / g), ferment at 35°C for 72 hours to degrade lignin and improve fiber digestibility.

[0169] Step 2: Pretreatment with complex enzyme preparation

[0170] Mix the complex enzyme preparation (xylanase, cellulase, β-glucanase) with water at a ratio of 1:10 and activate it at 30°C for 2 hours.

[0171] After activation, add it to the feed and mix evenly to improve enzyme activity and degradation efficiency.

[0172] Step 3: Feed mixing and granulation

[0173] Weigh each component according to the formula ratio and mix them in the following order:

[0174] First, mix corn, wheat bran, and DDGS.

[0175] Then add fish meal, corn protein powder, fermented soybean residue, and microbially fermented straw and stir well.

[0176] Finally, add mineral element premix, vitamin premix, complex enzyme preparation, and microecological preparation and stir evenly.

[0177] Use a ring die granulator to control the granulation temperature at 70 - 80°C and the moisture at 12% - 14%, and extrude and granulate to form 3 - 6 mm pellet feed.

[0178] After granulation, cool it by air cooling to room temperature, and package and store it in a sealed manner.

[0179] Step 4: Detection of nutritional components

[0180] Determination of crude protein content (Kjeldahl method)

[0181] Take 2 g of feed sample, digest it with concentrated sulfuric acid, add alkaline reagent for distillation, titrate to calculate the total nitrogen content, and finally calculate the crude protein content (%).

[0182] Determination of metabolic energy (bomb calorimetry)

[0183] Take 1 g of dry feed, place it in a bomb calorimeter for combustion, measure the total energy released, and calculate the metabolizable energy value (MJ / kg).

[0184] Determination of crude fiber degradation rate

[0185] Take 3 g of feed sample, add gastric juice to simulate the digestive enzyme solution, shake and culture for 48 h, then measure the residual fiber content and calculate the crude fiber degradation rate (%).

[0186] 3. Fattening effect test

[0187] Experimental design

[0188] Select 60 healthy fattening cattle, randomly divide them into a control group (soybean meal-containing diet) and an experimental group (soybean meal-free diet), with 30 heads in each group.

[0189] The feeding period is 120 days, feeding 2 times a day, with free drinking water.

[0190] Growth performance measurement

[0191] Measure the weight of the cattle once every 30 days and record the average daily gain (kg).

[0192] Calculate the feed conversion ratio (FCR):

[0193] Experimental data and analysis

[0194] The growth performance comparison is as follows:

[0195] Technical Index Control Group (Containing Soybean Meal) Experimental Group (Without Soybean Meal) Improvement Effect Average Daily Gain (kg) 1.15±0.03 1.28±0.02 +11.3％ Feed Conversion Rate 5.2 4.7 +9.6％ Protein Absorption Rate 80.5％ 85.7％ +6.5％ Lignin Degradation Rate 30.1％ 46.8％ +55.5％

[0196] The economic benefit analysis is as follows:

[0197] Item Control Group (Containing Soybean Meal) Experimental Group (Without Soybean Meal) Change Rate (%) Feed Cost (yuan / kg) 3.80 3.40 -10.5％ Finishing Period (days) 180 465 -8.3％ Profit (yuan / head) 2660 4090 +53.8％

[0198] Conclusion, optimization of nutritional components: The crude protein, metabolizable energy, and crude fiber degradation rate in the experimental group are all improved, and the fattening effect is better. Improvement in growth performance: The daily gain is increased by 11.3%, the fattening period is shortened by 8.3%, and the economic benefit is significant. Complete substitution of soybean meal: Reduce the dependence on soybean meal, improve the sustainability of feed, and reduce the breeding cost. The formula and preparation method of the present invention can be widely applied to large-scale breeding to improve the fattening efficiency of ruminants.

[0199] Although the present invention has been disclosed above with preferred embodiments, it is not intended to limit the present invention. Those with ordinary knowledge in the technical field to which the present invention pertains can make various modifications and refinements without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be determined by what is defined in the claims.

Claims

1. A formula of a soybean meal-free diet feed for fattening ruminants, characterized in that: The formula composition is calculated by mass percentage as follows: Corn 30-40%, wheat bran 8-12%, corn distiller's grains 10-15%, cottonseed meal 8-12%, rapeseed meal 5-10%, fish meal 3-5%, corn gluten meal 3-6%, fermented bean dregs 5-8%, microbial fermentation straw 6-10%, yeast culture 2-4%, mineral element premix 1.5-2.5%, vitamin premix 1-2%, complex enzyme preparation 0.3-0.7%, and probiotic preparation 0.5-1%.

2. The formula of a soybean meal-free daily feed for fattening ruminants according to claim 1, characterized in that: The microecological preparation is lactic acid bacteria or bacillus.

3. The formula of a soybean meal-free daily feed for fattening ruminants according to claim 1, characterized in that: Yeast culture includes beta-glucan, mannan, yeast protein, lactic acid, active yeast strains, nucleotides, and B vitamins; The mineral element premix is ​​used to supplement the essential minerals required for the growth of ruminants, and includes the following ingredients: calcium carbonate, monocalcium phosphate, magnesium oxide, sodium chloride, potassium chloride, sodium sulfate, zinc oxide, copper methionine, ferrous sulfate, manganese methionine, selenium yeast and calcium iodate; Vitamin premix includes vitamin A, vitamin D3, vitamin E, vitamin K3, vitamin B1, vitamin B2, vitamin B6, niacin, pantothenic acid, folic acid, biotin and vitamin B 12 .

4. A method for preparing a soybean meal-free diet feed for fattening ruminants, characterized in that: The steps include: Step 1, raw material selection and pretreatment, select raw materials and use MOPSO to calculate the optimal raw material ratio, with cost, protein content and metabolic energy as optimization targets. Pretreatment includes detoxification and fermented bean dregs preparation; Step 2: Microbial fermentation straw preparation, using LSTM to predict corn straw degradation progress and optimize enzymatic hydrolysis efficiency; Step 3: Pretreatment of compound enzyme preparation. The neural network predicts the optimal activation conditions for enzyme activity. The compound enzyme preparation includes xylanase, cellulase, and β-glucanase. The compound enzyme preparation is mixed with water at a ratio of 1:10, and the temperature is controlled by AI. Step 4: Feed mixing and granulation. First, mix corn, wheat bran and DDGS; then add cottonseed meal, rapeseed meal, fish meal, corn protein meal, fermented bean dregs, and microbial fermented straw; finally, add mineral element premix, vitamin premix, complex enzyme preparation, and microecological preparation. Use a ring die pelletizer to optimize temperature control and use AI to adjust moisture. Control particle size and optimize feed uniformity. Use AI to adjust compression force and reduce breakage rate. Cool with air to room temperature and then seal and package.

5. The method for preparing a soybean meal-free diet feed for fattening ruminants according to claim 4, characterized in that: In step 1, the raw materials are selected and the optimal raw material ratio is calculated using MOPSO: F(X): Optimize the objective function, the smaller the better; C(X): feed cost (yuan / kg), optimize cost control; P(X): crude protein content of feed (%), to ensure nutritional balance; E(X): metabolizable energy (MJ / kg), improves digestibility; ω1, ω2, ω3: weight factors, adaptively adjusted by the neural network; P opt : Target crude protein content; E opt : Target metabolic energy; The raw materials are corn, wheat bran, DDGS, cottonseed meal, rapeseed meal, fish meal, corn gluten meal, fermented soybean dregs, and microbial fermented straw; Detoxification treatment: cottonseed meal and rapeseed meal need to remove free gossypol and glucosinolate to reduce toxic side effects; Intelligent temperature control for fermented okara preparation: adjust the moisture content to 60%; AI Optimized Temperature Control: T(t+1)=T(t)+k1(T opt -T(t))+k2Σe t +k3(e t -e t-1 ); T(t+1): temperature at time t+1; T(t): temperature at time t; T opt : Optimal fermentation temperature; k1, k2, k3: temperature adjustment coefficients; e t =T opt -T(t): temperature deviation; e t-1 : Temperature deviation at the last moment; Inoculate lactic acid bacteria, yeast, Bacillus subtilis, 10 per gram 7 CFU; Closed fermentation for 48 hours, AI dynamically adjusts the temperature to improve protein solubility.

6. The method for preparing a soybean meal-free diet feed for fattening ruminants according to claim 4, characterized in that: In step 2, LSTM (Long Short-Term Memory Neural Network) is used to predict the degradation progress and optimize the enzymatic hydrolysis efficiency: E dose (t): enzyme dosage at time t; S(t): undegraded cellulose content; t opt : Optimal enzymatic hydrolysis time; α is the reaction rate coefficient determined by PSO; The specific operation is to take corn stalks and crush them into 3-5 mm particle size; adjust the moisture to 60%, add 3% corn syrup or glucose as carbon source; inoculate mixed bacteria actinomycetes, Aspergillus niger, and lactic acid bacteria, with a dosage of 10 8 CFU / g; AI controls temperature and humidity, dynamically regulates enzyme input, and ferments for 72 hours.

7. The method for preparing a soybean meal-free diet feed for fattening ruminants according to claim 4, characterized in that: In step 3, the neural network predicts the optimal activation conditions for enzyme activity: T opt : Optimal activation temperature; T initial : initial temperature; γsin(ωt): compensation for environmental fluctuations; When AI regulates the temperature, the initial temperature is 30°C and then gradually adjusted to the optimal temperature; activate for 2 hours and stir evenly to increase enzyme activity.

8. The method for preparing a soybean meal-free diet feed for fattening ruminants according to claim 4, characterized in that: In step 4, an intelligent granulation optimization formula is used to optimize the uniformity and mechanical stability of feed granulation: P opt : Optimal granulation parameters; U(P): particle uniformity score, the higher the better; L(P): granulation loss, the smaller the better; k6, k7: optimization weight coefficients.

Images