High-tower compound fertilizer added with biological fungicide, preparation method and fungicide adding method

Abstract

The invention belongs to the technical field of microbial fertilizer preparation, and discloses a high-tower compound fertilizer added with a biological fungicide, a preparation method and a fungicide adding method. Comprising the following steps: determining high-tower compound fertilizer preparation steps; collecting fertilizer characteristic parameters; predicting the preparation process temperature according to the characteristic parameters of the fertilizer; fusing the characteristic parameters of the fertilizer and the temperature of the preparation process to determine the characteristic parameters of the fungicide; based on the microbial agent characteristic parameters and the preparation process temperature, the microbial agent adding time is set; according to the preparation process temperature and the microbial inoculum characteristic parameters, executing a high-tower compound fertilizer preparation step, and when the microbial inoculum is added, collecting and analyzing a particle image to obtain fertilizer particle parameters; based on the fertilizer particle parameters and the microbial agent characteristic parameters, determining and executing a microbial agent mixing mode; the activity and stability of the microbial inoculum can be effectively guaranteed, the fertilizer efficiency of the high-tower compound fertilizer is improved, and the effects of microorganisms in improving soil fertility and promoting plant growth are fully exerted.

Description

Technical Field

[0001] The present invention relates to the technical field of microbial fertilizer preparation, and more specifically, to a high tower compound fertilizer added with a biological bactericide, a preparation method, and a bactericide addition method. Background Art

[0002] High tower compound fertilizer is a compound fertilizer produced by the high tower process, which has advantages such as good uniformity and strong solubility; adding a biological bactericide to the high tower compound fertilizer can further improve its fertilizer effect; the biological bactericide can enhance the activity of the soil microbial community through various ways such as nitrogen fixation, decomposition of organic matter, and promotion of nutrient element absorption, thereby optimizing the absorption and utilization of plant nutrients; however, the existing bactericide addition methods often fail to fully consider the stability and activity of microorganisms in the fertilizer, resulting in a significant reduction in the effect of the bactericide; therefore, exploring an effective bactericide addition method to ensure the effective addition and long-term activity of the biological bactericide in the high tower compound fertilizer has become the focus of current research.

[0003] Chinese Patent with Publication No. CN113754493A discloses a preparation method of a high tower compound fertilizer based on an enzyme biological bactericide; it includes: preparing a high tower biological bactericide: mixing one or more of Paenibacillus mucilaginosus, Bacillus amyloliquefaciens, Bacillus subtilis, and Bacillus licheniformis to prepare a bactericide; preparing a high tower biological bacterial fertilizer: putting the following components in weight ratio into the high tower: 30% urea, 3% ammonium sulfate with a concentration of 21%, 10.5% phosphoric acid ammonium with a concentration of 55%, 11% potassium sulfate with a concentration of 50%, 45.5% enzyme powder, then performing high-temperature chelation, three-stage pulping, and granulating after uniform chelation; fertilizer coating: coating the granulated biological bacterial fertilizer with an anti-caking agent, and then uniformly adding the bactericide; this invention uses enzyme organic as a carrier, so that the biological bactericide can be effectively added during the production process of the high tower compound fertilizer, which can effectively improve the survival rate and efficacy of the preserved bacteria, has a good strengthening effect on the fertilizer efficiency of the biological fertilizer, and has problems such as small fertilizer pollution and not easy to cause soil compaction.

[0004] However, in the process of preparing the fertilizer (high tower compound fertilizer) in the above technology, the components in the enzyme powder, high tower biological bactericide, and high tower biological bacterial fertilizer are all prepared. However, the components of different fertilizers are different, and the corresponding suitable bactericides are also different. If the same pre-configured bactericide is used, the microorganisms in the bactericide may not adapt to different fertilizers, affecting the stability and activity of microorganisms in the fertilizer, thereby affecting the effect of the bactericide in the fertilizer; in addition, the addition timing, addition amount, mixing method, etc. of the bactericide will also affect the stability and activity of microorganisms in the fertilizer, and should be dynamically optimized according to the specific situation of the fertilizer.

[0005] In view of this, the present invention proposes a high tower compound fertilizer added with a biological bactericide, a preparation method, and a bactericide addition method to solve the above problems. Summary of the Invention

[0006] To overcome the above defects of the prior art and achieve the above object, the present invention provides the following technical solutions:

[0007] Preparation method of tower compound fertilizer added with biological bacteria agent, comprising:

[0008] S1: Determine the preparation steps of tower compound fertilizer;

[0009] S2: Collect fertilizer characteristic parameters;

[0010] S3: Predict the preparation process temperature according to the fertilizer characteristic parameters;

[0011] S4: Integrate the fertilizer characteristic parameters and the preparation process temperature to determine the bacteria agent characteristic parameters;

[0012] S5: Set the bacteria agent addition timing based on the bacteria agent characteristic parameters and the preparation process temperature;

[0013] S6: According to the preparation process temperature and the bacteria agent characteristic parameters, execute the preparation steps of tower compound fertilizer. When it reaches the bacteria agent addition timing, collect the particle images, analyze the particle images, and obtain the fertilizer particle parameters;

[0014] S7: Determine the bacteria agent mixing method based on the fertilizer particle parameters and the bacteria agent characteristic parameters;

[0015] S8: Mix the bacteria agent and the tower compound fertilizer according to the bacteria agent mixing method, and continue to execute the preparation steps of tower compound fertilizer.

[0016] Further, the preparation steps of the tower compound fertilizer include:

[0017] Step S101: Raw material preparation;

[0018] Step S102: Raw material mixing;

[0019] Step S103: Granulation;

[0020] Step S104: Drying;

[0021] Step S105: Cooling;

[0022] Step S106: Screening and grading;

[0023] Step S107: Packaging and storage.

[0024] Furthermore, the fertilizer characteristic parameters include fertilizer component parameters, raw material proportion parameters, and fertilizer use parameters; the fertilizer component parameters are the raw material types of the tower compound fertilizer; the raw material proportion parameters are the mass proportions of each raw material in the tower compound fertilizer; the fertilizer use parameters include the target crop and soil type; the target crop is the object of action of the tower compound fertilizer; the soil type is the soil type when the target crop grows.

[0025] The preparation process temperature includes granulation temperature, drying temperature, and cooling temperature.

[0026] The method for predicting the preparation process temperature includes:

[0027] Set different digital tags for different raw material types, target crops, and soil types respectively, convert the fertilizer component parameters and fertilizer use parameters into corresponding digital tags, and mark them as raw material tags, crop tags, and soil tags respectively; obtain the temperature adjustment range, which includes the granulation temperature range, drying temperature range, and cooling temperature range; randomly select a value from each range in the temperature adjustment range to construct a test set, a total of b test sets are constructed, set different digital tags for each test set, and mark them as set tags; use the raw material tags, crop tags, soil tags, and raw material proportion parameters as analysis data, input the analysis data into the trained temperature prediction model, predict the corresponding set tag, and obtain the corresponding preparation process temperature according to the predicted set tag.

[0028] Furthermore, the method for determining the microbial agent characteristic parameters includes:

[0029] Step S401: Preset the initial temperature T max , the lowest temperature T min , the cooling coefficient δ, and the maximum number of iterations ξ, and let the current temperature T = T max ;

[0030] Step S402: Preset m groups of microbial agent characteristic parameters, where m is an integer greater than 1; randomly set a feasible solution χ, and the feasible solution χ is the microbial agent characteristic parameter, and the range of the feasible solution χ is m groups of microbial agent characteristic parameters;

[0031] Step S403: Determine the fitness function;

[0032] The expression of the fitness function is: f = pc; where f is the fitness and pc is the matching degree.

[0033] Step S404: Calculate the fitness f corresponding to the feasible solution χ; use the feasible solution χ as the current point, perform random perturbation in the neighborhood of the current point to obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′.

[0034] Step S405: Calculate the fitness difference f″; if the fitness difference f″ > 0, then let χ = χ′; if the fitness difference f″ ≤ 0, then calculate the probability p′, and let χ = χ′ according to the probability p′;

[0035] Step S406: Loop steps S404 to S405 until the number of loops reaches the maximum number of iterations ξ, then the loop ends; let the current temperature T = T × δ; let the maximum number of iterations ξ = ξ × δ;

[0036] Step S407: Loop steps S404 to S406 until the current temperature T < T min When the loop ends, obtain the bacterial agent characteristic parameters corresponding to the feasible solution χ.

[0037] Furthermore, the bacterial agent characteristic parameters include bacterial agent component parameters and component content parameters; the bacterial agent component parameters are the types of bacterial strains in the bacterial agent; the component content parameters are the contents corresponding to each type of bacterial strain in the bacterial agent;

[0038] In the step S403, the method for obtaining the matching degree is as follows: use the bacterial agent characteristic parameters, analysis data, and preparation process temperature corresponding to the feasible solution χ as test data; input the test data into the trained matching prediction model to predict the corresponding matching degree; the training process of the matching prediction model is the same as that of the temperature prediction model, and both are deep neural network models;

[0039] In the step S405, the expression of the fitness difference f″ is f″ = f′ - f; the expression of the probability p′ is: In the formula, e is the natural constant.

[0040] Furthermore, the particle image is an image of the high - tower compound fertilizer particles during the preparation process of the high - tower compound fertilizer; the fertilizer particle parameters include particle size and particle shape;

[0041] The steps for obtaining the fertilizer particle parameters include:

[0042] Step S601: Perform grayscale processing on the particle image to obtain a grayscale image;

[0043] Step S602: Perform image segmentation on the grayscale image to segment the particle regions in the grayscale image;

[0044] Step S603: Use a contour detection algorithm to extract the contour of each particle from the particle region;

[0045] Step S604: According to the contour of each particle, calculate the area of each particle and use it as the particle size;

[0046] Step S605: According to the contour of each particle, calculate the solidity of each particle and use it as the particle shape.

[0047] Further, in the step S602, the method for segmenting the particle region in the grayscale image is as follows: preset a grayscale value threshold; obtain the grayscale value of each pixel point in the grayscale image, and compare it with the grayscale value threshold respectively. Mark the pixel points with grayscale values greater than or equal to the grayscale value threshold as particle points, and do not mark the pixel points with grayscale values less than the grayscale value threshold; segment the grayscale image according to the particle points in the grayscale image to segment out the particle region;

[0048] In the step S604, the method for calculating the area of each particle is as follows: obtain the boundary point coordinates corresponding to each particle contour, and calculate the area of each particle; the boundary point coordinates are the coordinates of the pixel points located on the boundary of the particle contour; the expression for the particle area is: where S is the particle area, x i is the abscissa of the i-th boundary point coordinate, and y i+1 is the ordinate of the (i + 1)-th boundary point coordinate, i ∈ [1, n], and n is the number of boundary point coordinates; among them, if i = n, then i + 1 = 1;

[0049] In the step S605, the method for calculating the solidity of each particle is as follows: adopt the convex hull algorithm to calculate the convex hull corresponding to each particle contour, obtain the vertex coordinates of the convex hull corresponding to each particle contour, and mark them as convex hull coordinates; calculate the area of the convex hull corresponding to each particle according to the convex hull coordinates, and the calculation method of the convex hull area is the same as that of the particle area; divide the particle area of each particle by the corresponding convex hull area to obtain the solidity of each particle.

[0050] The method for adding the microbial agent is implemented according to the method for preparing the tower compound fertilizer with added biological microbial agent described above. The method for adding the microbial agent includes setting the timing of adding the microbial agent and determining the mixing method of the microbial agent;

[0051] The method for setting the timing of adding the microbial agent includes:

[0052] Preset a strain-temperature mapping table, where the strain-temperature mapping table includes strain labels and the corresponding temperature ranges; the strain labels are digital labels corresponding to strain types, and different strain types correspond to different digital labels;

[0053] According to the characteristics parameters of the microbial agent, obtain the corresponding strain labels, and then according to the strain-temperature mapping table, obtain the temperature range corresponding to each strain type and mark it as the suitable temperature range; sort each temperature in the preparation process temperature according to the order of the high tower compound fertilizer preparation steps to obtain the temperature order, that is, the temperature order is the granulation temperature, the drying temperature and the cooling temperature; compare each suitable temperature range with each temperature in the preparation process temperature respectively according to the temperature order; mark the temperature whose values are all within each suitable temperature range in the preparation process temperature as the suitable temperature;

[0054] If each temperature in the preparation process temperature is marked as the suitable temperature, set the timing of microbial agent addition before the start of the granulation process in step S103;

[0055] If the drying temperature and the cooling temperature are marked as the suitable temperature, set the timing of microbial agent addition before the start of the drying process in step S104;

[0056] If the cooling temperature is marked as the suitable temperature, but the drying temperature is not marked as the suitable temperature, set the timing of microbial agent addition before the start of the cooling process in step S105;

[0057] If each temperature in the preparation process temperature is not marked as the suitable temperature, set the timing of microbial agent addition before the start of the screening and grading process in step S106.

[0058] Furthermore, the steps of determining the mixing method of the microbial agent include:

[0059] Step S701: Establish fuzzy sets, and divide each fertilizer particle parameter and microbial agent characteristic parameter into multiple fuzzy sets;

[0060] Step S702: Convert the fertilizer particle parameters and microbial agent characteristic parameters into the membership degrees of the corresponding each fuzzy set respectively through the fuzzification technology; fuzzification is the process of converting accurate numerical values into the membership degrees corresponding to fuzzy sets;

[0061] Step S703: Define fuzzy rules;

[0062] Step S704: Match the fuzzified fertilizer particle parameters and microbial agent characteristic parameters with the fuzzy rules, perform fuzzy inference, and obtain the fuzzy inference result, and the fuzzy inference result is the membership degree corresponding to each microbial agent mixing method;

[0063] Step S705: Perform defuzzification operation on the fuzzy inference result to obtain the defuzzification result, and the defuzzification result is the determined mixing method of the microbial agent; the defuzzification operation is: according to the fuzzy inference result, compare the membership degrees corresponding to each microbial agent mixing method respectively, and take the mixing method corresponding to the maximum membership degree value as the mixing method of the microbial agent adopted in the high tower compound fertilizer preparation process.

[0064] The tower compound fertilizer added with biological bacterial agents is prepared according to the preparation method of the tower compound fertilizer added with biological bacterial agents as described.

[0065] The technical effects and advantages of the tower compound fertilizer added with biological bacterial agents, the preparation method and the bacterial agent addition method of the present invention are as follows:

[0066] By collecting fertilizer characteristic parameters in real time, gradually predicting the preparation process temperature, the bacterial agent characteristic parameters and the bacterial agent addition timing, the dynamic addition of the bacterial agent at an appropriate timing during the preparation process of the tower compound fertilizer is realized; the fuzzy logic control method is adopted to realize the optimized selection of the bacterial agent mixing method; ensuring the effective addition of the biological bacterial agent in the tower compound fertilizer, and ensuring the activity and stability of the bacterial agent; not only improving the fertilizer efficiency of the tower compound fertilizer, but also improving the soil microbial community; thereby optimizing the absorption of plant nutrients and giving full play to the role of microorganisms in improving soil fertility and promoting plant growth, overcoming the problem of the decline of the activity of the bacterial agent in the traditional method, and promoting the development of sustainable agriculture. Brief Description of the Drawings

[0067] Figure 1 It is a flow chart of the preparation method of the tower compound fertilizer added with biological bacterial agents in Embodiment 1 of the present invention;

[0068] Figure 2 It is a flow chart of the method for determining the bacterial agent characteristic parameters in Embodiment 1 of the present invention;

[0069] Figure 3 It is a flow chart of the method for determining the bacterial agent mixing method in Embodiment 1 of the present invention. Detailed Embodiments

[0070] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0071] Embodiment 1

[0072] Please refer to Figure 1 As shown, this embodiment provides a preparation method and a bacterial agent addition method for a tower compound fertilizer added with biological bacterial agents. The method includes:

[0073] S1: Determine the preparation steps of the tower compound fertilizer.

[0074] The tower compound fertilizer is a compound fertilizer mainly composed of nitrogen, phosphorus and potassium, usually produced by the tower process, and is widely used in agriculture, especially for fertilizing field crops, fruit trees and vegetables.

[0075] The preparation steps of the high tower compound fertilizer include:

[0076] Step S101: Raw material preparation;

[0077] The raw materials of the high tower compound fertilizer mainly include nitrogen sources (such as urea), phosphorus sources (such as ammonium phosphate), potassium sources (such as potassium chloride), trace elements (such as zinc, iron, etc.), and other additives (such as organic matter).

[0078] Step S102: Raw material mixing;

[0079] Mix various raw materials evenly in a mixer to ensure that different components are fully combined.

[0080] Step S103: Granulation;

[0081] Feed the mixed raw materials into high tower granulation equipment, and granulate the mixed materials in the high tower through methods such as spray granulation or fluidized granulation; Spray granulation is to spray liquid fertilizer (such as liquid nitrogen source) into the particles to promote the formation of particles; Fluidized granulation is to suspend the mixed materials through air flow, increase the contact area of the particles, and promote the growth of particles.

[0082] Step S104: Drying;

[0083] Use a dryer to evaporate the moisture in the particles through hot air or other heating methods to ensure the drying and stability of the particles.

[0084] Step S105: Cooling;

[0085] Cool the dried particles to room temperature through a cooler to avoid caking of the particles during storage and transportation.

[0086] Step S106: Screening and grading;

[0087] Screen the particles through a sieve to remove too large or too small particles to ensure the uniformity of the product; and grade according to the particle size to meet market demands; For example, some crops may be more suitable for using small particle fertilizers for easy root absorption; while other crops may require large particle fertilizers to slow down nutrient release.

[0088] Step S107: Packaging and storage;

[0089] Package the graded particles and use appropriate materials to prevent moisture and protect the particles; After packaging, store them in a dry and cool environment to maintain the stability and effectiveness of the high tower compound fertilizer.

[0090] S2: Collect fertilizer characteristic parameters.

[0091] Fertilizer characteristic parameters include fertilizer component parameters, raw material proportion parameters, and fertilizer usage parameters; the fertilizer component parameters are the raw material types of the tower compound fertilizer; the raw material proportion parameters are the mass proportions of each raw material in the tower compound fertilizer; the fertilizer usage parameters include target crops and soil types; the target crops are the objects of action of the tower compound fertilizer, such as food crops (such as wheat, corn, rice, etc.), cash crops (such as cotton, rapeseed, etc.), fruit trees, etc.; the soil type is the type of soil when the target crop grows, such as sandy soil, clay soil, loam soil, etc.

[0092] The fertilizer component parameters are obtained through a near-infrared spectroscopy sensor or a Fourier transform infrared spectroscopy sensor installed at the feed inlet of the mixer according to a preset collection interval; the fertilizer usage parameters are all obtained by input from relevant staff.

[0093] The method for obtaining the raw material proportion parameters includes:

[0094] Continuously collect the mass of the mixed raw materials according to a preset collection interval. The mass of the mixed raw materials is the total mass of the raw materials in the mixer and is obtained by a mass sensor installed in the mixer. The collection interval is preset by those skilled in the art according to the actual situation; compare all the collected masses of the mixed raw materials, and mark the masses of the mixed raw materials with the same value as the same mass; mark the time points corresponding to the same mass as the stop points; mark the earliest stop point among the continuous stop points as the end point, and mark the latest stop point among the continuous stop points as the start point; regard each start point, end point, and the intermediate time points as an analysis set.

[0095] Obtain the time points corresponding to each time the fertilizer component parameters are collected and mark them as collection points; mark the latest collection point among the continuous collection points as the termination point; compare each termination point with the time points in each analysis set respectively. If the termination point coincides with the time point in the analysis set, the raw material type corresponding to the analysis set is the raw material type collected at the corresponding termination point. If the termination point does not coincide with any time point in the analysis set, then use the analysis set where the time point closest to the time of the corresponding termination point is located as the analysis set corresponding to the corresponding termination point, and use the raw material type collected at the corresponding termination point as the raw material type of the corresponding analysis set.

[0096] Obtain the mass of the mixed raw materials corresponding to the end points in each analysis set, compare two adjacent end points, mark the latest end point as the first end point, and mark the earliest end point as the second end point; subtract the mass of the mixed raw materials corresponding to the second end point from the mass of the mixed raw materials corresponding to the first end point, and use it as the mass of the raw material type corresponding to the analysis set corresponding to the first end point, and mark it as the raw material mass; among them, the raw material mass corresponding to the analysis set corresponding to the first end point is the mass of the mixed raw materials corresponding to the first end point; divide the raw material mass of each raw material type by the mass of the mixed raw materials corresponding to the last end point respectively to obtain the mass percentage of each raw material type, that is, obtain the raw material percentage parameter.

[0097] Exemplarily, urea, ammonium phosphate and potassium chloride enter the mixer in sequence. The time points when the near-infrared spectrum sensor collects urea are 1, 2, 3, the time points when it collects ammonium phosphate are 6, 7, 8, and the time points when it collects potassium chloride are 10, 11, 12; therefore, the time points 3, 8 and 12 are termination points; the mass sensor starts collecting the mass of the mixed raw materials at time point 2, which are 1, 2, 4, 4, 4, 6, 7, 8, 8, 9, 11, 13 in sequence, corresponding to time points 2 - 13 respectively; therefore, time points 4 - 6 and 9 - 10 are marked as suspension points, time points 4, 9, 13 are end points, and time points 1, 6, 10 are start points; time points 1 - 4 are the first analysis set, time points 6 - 9 are the second analysis set, and time points 10 - 13 are the third analysis set; since the termination point 3 is in the first analysis set, the first analysis set corresponds to urea, and the raw material mass of urea is 4; since the termination point 8 is in the second analysis set, the second analysis set corresponds to ammonium phosphate, and the raw material mass of ammonium phosphate is 8 - 4 = 4; since the termination point 12 is in the third analysis set, the third analysis set corresponds to potassium chloride, and the raw material mass of potassium chloride is 13 - 8 = 5; the mass percentages of urea and ammonium phosphate are respectively The mass percentage of potassium chloride is

[0098] S3: Predict the preparation process temperature according to the fertilizer characteristic parameters.

[0099] The preparation process temperature includes granulation temperature, drying temperature and cooling temperature.

[0100] The methods for predicting the preparation process temperature include:

[0101] Different digital tags are set for different raw material types, target crops, and soil types respectively. The fertilizer component parameters and fertilizer use parameters are converted into corresponding digital tags, and are respectively marked as raw material tags, crop tags, and soil tags. According to the technical parameters corresponding to the tower granulation equipment, dryer, and cooler, the corresponding temperature adjustment range is obtained, and the temperature adjustment range includes the granulation temperature range, drying temperature range, and cooling temperature range. A value is randomly selected from each range in the temperature adjustment range to construct a test set. A total of b test sets are constructed, and different digital tags are set for each test set and marked as set tags. The raw material tags, crop tags, soil tags, and raw material proportion parameters are used as analysis data, and the analysis data is input into the trained temperature prediction model to predict the corresponding set tag. According to the predicted set tag, the corresponding preparation process temperature is obtained.

[0102] The specific training process of the temperature prediction model includes:

[0103] A set of set tags corresponding to a group of analysis data is collected in advance, where a is an integer greater than 1. The analysis data and the corresponding set tags are converted into a corresponding set of feature vectors. The set tags corresponding to the analysis data are collected by those skilled in the art during the historical preparation process of tower compound fertilizers. A group of different analysis data is collected, and multiple preparation experiments are carried out in sequence under the conditions of each group of analysis data. Moreover, the preparation process temperatures in different preparation experiments corresponding to the same analysis data are different. After each preparation is completed, the quality of the tower compound fertilizer is analyzed according to actual experience. The set tag corresponding to the test set corresponding to the preparation process temperature adopted in the preparation process of the tower compound fertilizer with the best quality is used as the set tag corresponding to this group of analysis data. And so on, the set tags corresponding to each group of analysis data are obtained, and corresponding set tags are set for a groups of analysis data respectively;

[0104] Each group of feature vectors is used as the input of the temperature prediction model. The temperature prediction model takes a set of set tags corresponding to each group of analysis data as the output, and takes the actual set tag corresponding to each group of analysis data as the prediction target. The actual set tag is the set tag corresponding to the analysis data collected in advance; minimizing the sum of the prediction errors of all analysis data is used as the training target; among them, the calculation formula of the prediction error is where ν K is the prediction error, K is the group number of the feature vectors corresponding to the analysis data, is the set tag corresponding to the Kth group of analysis data, and β K is the actual set tag corresponding to the Kth group of analysis data; the temperature prediction model is trained until the sum of the prediction errors reaches convergence and then the training stops;

[0105] The above temperature prediction model is specifically a deep neural network model.

[0106] It should be noted that the reason for using deep learning technology to predict the preparation process temperature is that deep learning technology can process complex high-dimensional data and is suitable for analyzing various characteristics such as fertilizer component parameters and raw material ratio parameters; and it can capture the non-linear relationship between input features and output features, which is suitable for describing the complex interaction relationship between fertilizer characteristic parameters and preparation process temperature; at the same time, by training a large amount of historical data, deep learning technology can improve the accuracy of temperature prediction, thereby optimizing the preparation process and improving the quality of fertilizers; in addition, the model can be retrained by continuously inputting new data to adapt to new raw material characteristics or production process changes and maintain the effectiveness of prediction.

[0107] S4: Integrate fertilizer characteristic parameters and preparation process temperature to determine the inoculant characteristic parameters.

[0108] The inoculant characteristic parameters include inoculant component parameters and component content parameters; the inoculant component parameters are the types of strains in the inoculant, such as nitrogen-fixing bacteria (such as rhizobia, blue-green algae), phosphorus-solubilizing bacteria (such as phosphate-solubilizing bacteria, Aspergillus), root-promoting bacteria (such as arbuscular mycorrhizal fungi, rhizosphere bacteria), etc.; the component content parameters are the contents corresponding to each strain type in the inoculant.

[0109] Such as Figure 2 shown, the method for determining the inoculant characteristic parameters includes:

[0110] Step S401: Preset the initial temperature T max , the lowest temperature T min , the cooling coefficient δ and the maximum number of iterations ξ, and let the current temperature T = T max .

[0111] Step S402: Preset m groups of inoculant characteristic parameters, where m is an integer greater than 1; randomly set a feasible solution χ, and the feasible solution χ is the inoculant characteristic parameter, and the range of the feasible solution χ is m groups of inoculant characteristic parameters; among them, the m groups of inoculant characteristic parameters are obtained by those skilled in the art according to the inoculant characteristic parameters used when successfully preparing tower compound fertilizers during the historical tower compound fertilizer preparation process.

[0112] Step S403: Determine the fitness function;

[0113] The expression of the fitness function is: f = pc;

[0114] In the formula, f is the fitness and pc is the matching degree;

[0115] The method for obtaining the matching degree is as follows: The bacterial agent characteristic parameters, analysis data, and preparation process temperature corresponding to the feasible solution χ are used as test data; the test data is input into the trained matching prediction model to predict the corresponding matching degree; the specific training process of the matching prediction model is the same as that of the temperature prediction model, and both are deep neural network models.

[0116] Step S404: Calculate the fitness f corresponding to the feasible solution χ; take the feasible solution χ as the current point, perform random perturbation within the neighborhood of the current point to obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′.

[0117] Step S405: Calculate the fitness difference f″, and the expression of the fitness difference f″ is f″ = f′ - f; if the fitness difference f″ > 0, then let χ = χ′, that is, assign the value of the new feasible solution χ′ to the feasible solution χ; if the fitness difference f″ ≤ 0, then calculate the probability p′, and let χ = χ′ according to the probability p′; the expression of the probability p′ is: In the formula, e is the natural constant.

[0118] Step S406: Loop steps S404 to S405 until the number of loops reaches the maximum iteration number ξ, then the loop ends; let the current temperature T = T × δ, that is, cool down the current temperature in step S401 and assign the cooled value to the current temperature; let the maximum iteration number ξ = ξ × δ, that is, assign the reduced value of the maximum iteration number to the maximum iteration number; if the reduced maximum iteration number is not an integer, then round up the reduced maximum iteration number to make it an integer.

[0119] Step S407: Loop steps S404 to S406 until the current temperature T < T min When the loop ends, obtain the bacterial agent characteristic parameters corresponding to the feasible solution χ.

[0120] It should be noted that the initial temperature T max 、the lowest temperature T min 、the cooling coefficient δ, and the maximum iteration number ξ are used as preset parameters. The preset parameters are determined by those skilled in the art. During the historical preparation process of tower compound fertilizers, c groups of different test data are collected, where c is an integer greater than 1. For a group of test data, multiple groups of different preset parameters are sequentially preset, and the bacterial agent characteristic parameters are obtained by using the simulated annealing algorithm in sequence. According to the obtained multiple groups of bacterial agent characteristic parameters, the matching degree with the actual experience analysis and the analysis data is combined, and the preset parameters corresponding to the maximum matching degree are used as the preset parameters corresponding to this group of test data. By analogy, the preset parameters corresponding to c groups of analysis data are obtained, and the average value of multiple preset parameters (i.e., the average value of the initial temperature, the average value of the lowest temperature, the average value of the cooling coefficient, and the average value of the maximum iteration number) is used as the preset initial temperature T in step S401max , the minimum temperature T min , the cooling coefficient δ, and the maximum number of iterations ξ.

[0121] It should be noted that the reason for using the simulated annealing algorithm to determine the characteristics parameters of the microbial agent is that the characteristics parameters of the microbial agent involve multiple dimensions and complex interrelationships. The simulated annealing algorithm can effectively avoid falling into local optimal solutions and is suitable for finding the global optimal solution in a complex parameter space. The simulated annealing algorithm can flexibly adjust the search strategy according to different preset parameters (such as temperature, cooling coefficient, etc.), enabling it to adapt to different application scenarios and objectives. The simulated annealing algorithm does not depend on a specific form of the objective function, can handle various types of fitness functions, has strong adaptability, and can be applied to the optimization problems of different microbial agent characteristics parameters.

[0122] S5: Set the timing of microbial agent addition based on the characteristics parameters of the microbial agent and the temperature of the preparation process.

[0123] The methods for setting the timing of microbial agent addition include:

[0124] Preset a strain-temperature mapping table. The strain-temperature mapping table is a two-dimensional mapping table, including strain labels and the temperature ranges corresponding to the strain labels. The strain label is a digital label corresponding to the strain type, and different strain types correspond to different digital labels. The temperature ranges corresponding to the strain types are obtained by those skilled in the art through consulting the literature and combining with practical experience.

[0125] According to the characteristics parameters of the microbial agent, obtain the corresponding strain labels. Then, according to the strain-temperature mapping table, obtain the temperature ranges corresponding to each strain type and mark them as the suitable temperature ranges. Sort each temperature in the preparation process temperature according to the order of the high tower compound fertilizer preparation steps to obtain the temperature order, that is, the temperature order is the granulation temperature, the drying temperature, and the cooling temperature. Compare each suitable temperature range with each temperature in the preparation process temperature respectively according to the temperature order. Mark the temperatures in the preparation process temperature whose values are all within each suitable temperature range as the suitable temperatures.

[0126] If each temperature in the preparation process temperature is marked as a suitable temperature, set the timing of microbial agent addition before the start of the granulation process in step S103;

[0127] If the drying temperature and the cooling temperature are marked as suitable temperatures, set the timing of microbial agent addition before the start of the drying process in step S104;

[0128] If the cooling temperature is marked as a suitable temperature, but the drying temperature is not marked as a suitable temperature, set the timing of microbial agent addition before the start of the cooling process in step S105;

[0129] If each temperature in the preparation process temperature is not marked as the suitable temperature, set the timing of inoculant addition before the screening and classification process in step S106.

[0130] It should be noted that the reason for setting the timing of inoculant addition according to the suitable temperature of the strain is that different strains show the best growth and activity within a specific temperature range. By judging the temperature, it can ensure that the inoculant is added to the preparation process of tower compound fertilizer within the suitable temperature range, thereby ensuring the microbial activity and improving the overall effect of tower compound fertilizer.

[0131] S6: According to the preparation process temperature and the characteristic parameters of the inoculant, perform the steps of preparing tower compound fertilizer. When it reaches the timing of inoculant addition, collect the particle image, analyze the particle image, and obtain the fertilizer particle parameters.

[0132] The particle image is the image of the tower compound fertilizer particles during the preparation process of tower compound fertilizer; the particle image is obtained by an image sensor installed in the tower; the fertilizer particle parameters include particle size and particle shape; it should be understood that the particle size affects the mixing uniformity: when the particle sizes are inconsistent, stratification is likely to occur: if the particle sizes of the tower compound fertilizer particles and the inoculant particles are quite different, stratification may occur during mixing due to different gravity and inertia; larger particles may settle faster, while smaller particles may float on the surface, resulting in uneven mixing; therefore, it is necessary to select an appropriate mixing method according to the particle size to ensure that particles of different sizes can be fully mixed; the particle shape affects the physical behavior of mixing: when the shape of the tower compound fertilizer particles is irregular, the contact surface between particles is larger, and friction and adhesion are likely to occur, affecting the fluidity of mixing; especially for the inoculant as a microbial agent, it may adhere to the surface of fertilizer particles and is not easy to disperse; therefore, it is necessary to select a suitable mixing method, such as using stirring mixing, drum mixing or fluidized bed mixing, etc., to reduce adhesion and accumulation problems.

[0133] The steps of obtaining the fertilizer particle parameters include:

[0134] Step S601: Perform grayscale processing on the particle image (such as weighted average method, maximum value method, Luminosity method, etc.) to obtain a grayscale image; to reduce the subsequent calculation complexity while retaining the particle shape and brightness information in the particle image;

[0135] Step S602: Perform image segmentation on the grayscale image to segment the particle region in the grayscale image; to separate the particle region in the grayscale image from the background for subsequent extraction of particle contours;

[0136] Step S603: Use a contour detection algorithm (such as Canny edge detection, Sobel operator, etc.) to extract the contour of each particle from the particle region; to facilitate subsequent calculation of the area and shape of each particle.

[0137] Step S604: Calculate the area of each particle based on the contour of each particle, and use it as the particle size;

[0138] Step S605: Calculate the solidity of each particle based on the contour of each particle, and use it as the particle shape.

[0139] In the above step S602, the method for segmenting the particle region in the grayscale image is as follows: preset a grayscale value threshold. The grayscale value threshold is obtained by those skilled in the art by collecting d grayscale images of particles during the historical preparation process of tower compound fertilizer, where d is an integer greater than 1, and converting them into grayscale images. Extract the grayscale values of the pixel points corresponding to the tower compound fertilizer particles in each grayscale image and mark them as particle grayscale values; obtain the minimum particle grayscale value in each grayscale image and take the average value as the grayscale value threshold; obtain the grayscale value of each pixel point in the grayscale image, and compare it with the grayscale value threshold respectively. Mark the pixel points with grayscale values greater than or equal to the grayscale value threshold as particle points, and do not mark the pixel points with grayscale values less than the grayscale value threshold; segment the grayscale image according to the particle points in the grayscale image to segment out the particle region.

[0140] It should be noted that in the grayscale image, since the tower compound fertilizer particles are usually relatively hard and smooth objects, they will reflect more light under light and present a higher grayscale value. Therefore, they appear as brighter regions in the grayscale image, that is, the grayscale value of the pixel points corresponding to the particles should be greater than the grayscale value of the pixel points corresponding to the background.

[0141] In the above step S604, the method for calculating the area of each particle is as follows: obtain the boundary point coordinates corresponding to the contour of each particle, and calculate the area of each particle; the boundary point coordinates are the coordinates of the pixel points located on the boundary of the particle contour; the expression for the particle area is: where S is the particle area, x i is the abscissa of the i-th boundary point coordinate, y i+1 is the ordinate of the (i + 1)-th boundary point coordinate, i ∈ [1, n], and n is the number of boundary point coordinates; among them, if i = n, then i + 1 = 1, because the n-th boundary point coordinate is adjacent to the 1st boundary point coordinate.

[0142] In the above step S605, the method for calculating the solidity of each particle is as follows: Using a convex hull algorithm (such as Graham scan method, Jarvis walk method, Andrew algorithm, etc.), calculate the convex hull corresponding to the contour of each particle, and obtain the vertex coordinates of the convex hull corresponding to the contour of each particle, and mark them as convex hull coordinates; Calculate the area of the convex hull corresponding to each particle according to the convex hull coordinates, and the calculation methods of the convex hull area and the particle area are the same; Divide the particle area of each particle by the corresponding convex hull area to obtain the solidity of each particle; It should be understood that, as a shape description parameter, the solidity can effectively reflect the regularity and complexity of the particle shape by comparing the actual area of the particle with its convex hull area; Regular particles (such as circles) have a solidity close to 1, indicating a smooth shape without depressions; Irregular particles have a lower solidity, indicating that there are more depressions or sharp corners on their boundaries and the shape is complex.

[0143] S7: Determine the mixing method of the microbial agent based on the fertilizer particle parameters and the microbial agent characteristic parameters.

[0144] Examples of the mixing method of the microbial agent include dry mixing (i.e., mixing the microbial agent with dry tower compound fertilizer), wet mixing (i.e., adding a small amount of water or liquid during the mixing of the microbial agent and dry tower compound fertilizer), embedding mixing (i.e., wrapping the microbial agent with an embedding material and then mixing it with tower compound fertilizer), etc.

[0145] Such as Figure 3 As shown, the steps for determining the mixing method of the microbial agent include:

[0146] Step S701: Establish a fuzzy set, and divide each fertilizer particle parameter and microbial agent characteristic parameter into multiple fuzzy sets; For example: The fuzzy sets corresponding to the particle size are small particle, medium particle, large particle, etc., the fuzzy sets corresponding to the particle shape are regular shape, slightly irregular shape, highly irregular shape, etc., and the fuzzy sets corresponding to the component content parameter are low content, medium content, high content, etc.;

[0147] Step S702: Respectively convert the fertilizer particle parameters and the microbial agent characteristic parameters into the membership degrees of the corresponding each fuzzy set through a fuzzification technique; Fuzzification is the process of converting accurate numerical values into the membership degrees corresponding to fuzzy sets, and fuzzification techniques such as triangular membership function, trapezoidal membership function, etc.; For example, if the numerical value of the particle size is low, the inferred membership degree of small particle is 0.8, the membership degree of medium particle is 0.2, and the membership degree of large particle is 0;

[0148] Step S703: Define fuzzy rules, which are defined based on expert knowledge or literature. For example, if the particles are small, regular in shape, medium in rhizobium content, and high in phosphate-solubilizing bacteria content, it is inferred that the mixing method of the microbial agent is embedding mixing to provide protection for the phosphate-solubilizing bacteria and ensure the activity of rhizobium in a moist environment. If the particles are medium-sized, severely irregular in shape, low in cyanobacteria content, and medium in arbuscular mycorrhizal fungi content, it is inferred that the mixing method of the microbial agent is wet mixing to ensure the dispersion of irregular particles and the proper protection of arbuscular mycorrhizal fungi.

[0149] Step S704: Match the fuzzified fertilizer particle parameters and microbial agent characteristic parameters with the fuzzy rules for fuzzy inference to obtain the fuzzy inference result, which is the membership degree corresponding to each mixing method of the microbial agent. The fuzzy inference method is, for example, Mamdani or Sugeno fuzzy inference method. The fuzzy inference result is, for example, the membership degree of dry mixing is 0.1, the membership degree of wet mixing is 0.3, and the membership degree of embedding mixing is 0.6.

[0150] Step S705: Perform defuzzification on the fuzzy inference result to obtain the defuzzification result, which is the determined mixing method of the microbial agent. Defuzzification is to convert the fuzzy inference result into a specific recognition result. The defuzzification operation is as follows: according to the fuzzy inference result, compare the membership degrees corresponding to each mixing method of the microbial agent respectively, and take the mixing method corresponding to the largest membership degree value as the mixing method of the microbial agent used in the preparation process of the tower compound fertilizer.

[0151] It should be noted that the reason for using the fuzzy logic control method to determine the mixing method of the microbial agent is that the fuzzy logic control method can convert the precise fertilizer particle parameters and microbial agent characteristic parameters into membership degrees in the fuzzy set, thereby effectively dealing with uncertainty and fuzziness, enabling the system to more flexibly cope with the complex preparation process of the tower compound fertilizer. In addition, the fuzzy logic control method combines fuzzy rules and inference methods, enabling the system to make intelligent decisions based on expert knowledge, being able to reason and make decisions independently according to the fertilizer particle parameters and microbial agent characteristic parameters obtained in real time, reducing human intervention, thereby improving the automation and intelligent level of the production process and ensuring that the selection of the mixing method is more flexible and efficient.

[0152] S8: Mix the microbial agent and the tower compound fertilizer according to the mixing method of the microbial agent, and continue to execute the tower compound fertilizer preparation steps.

[0153] In this embodiment, by collecting fertilizer characteristic parameters in real time, the preparation process temperature, the characteristics parameters of the microbial agent, and the addition timing of the microbial agent are gradually predicted, so as to realize the dynamic addition of the microbial agent at an appropriate time during the preparation of tower compound fertilizer; the fuzzy logic control method is adopted to realize the optimal selection of the mixing method of the microbial agent; ensure the effective addition of the biological microbial agent in the tower compound fertilizer, and ensure the activity and stability of the microbial agent; not only improve the fertilizer efficiency of the tower compound fertilizer, but also improve the soil microbial community; thereby optimizing the absorption of plant nutrients, giving full play to the role of microorganisms in improving soil fertility and promoting plant growth, overcoming the problem of the decline in the activity of the microbial agent in the traditional method, and promoting the development of sustainable agriculture.

[0154] Example 2

[0155] The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. Among them, computer-readable code is stored in the memory, and when the computer-readable code is run by one or more processors, it can execute the method for preparing a tower compound fertilizer with a biological microbial agent and the method for adding the microbial agent as described above.

[0156] The method or system according to the embodiment of the present application can also be implemented by means of the architecture of an electronic device. The electronic device may include a bus, one or more CPUs, a ROM, a RAM, a communication port connected to a network, an input / output, a hard disk, etc. The storage device in the electronic device, such as a ROM or a hard disk, can store the method for preparing a tower compound fertilizer with a biological microbial agent and the method for adding the microbial agent provided by the present application. Further, the electronic device may further include a user interface. Of course, when implementing different devices, one or more components in the electronic device may be omitted according to actual needs.

[0157] Example 3

[0158] One embodiment of the present application discloses a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are run by a processor, the method for preparing a tower compound fertilizer with a biological microbial agent and the method for adding the microbial agent provided according to the embodiment of the present application as described with reference to the above drawings can be executed. The storage medium includes but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0159] In addition, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be run by a processor to execute instructions corresponding to the method steps provided by the present application, such as: a method for preparing a high tower compound fertilizer by adding a biological inoculant and a method for adding the inoculant. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0160] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0161] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should all be included in the protection scope of the present invention.

Claims

1. A method for preparing high-tower compound fertilizer by adding biological agents, characterized in that: include: S1: Determine the steps for preparing high tower compound fertilizer; S2: Collect fertilizer characteristic parameters; S3: predict the preparation process temperature based on fertilizer characteristic parameters; S4: integrating the fertilizer characteristic parameters and the preparation process temperature to determine the characteristic parameters of the microbial agent; S5: Setting the timing of adding the inoculant based on the inoculant characteristic parameters and the preparation process temperature; S6: according to the preparation process temperature and the characteristic parameters of the microbial agent, the high tower compound fertilizer preparation steps are executed, and when the microbial agent is added, the particle image is collected, the particle image is analyzed, and the fertilizer particle parameters are obtained; S7: Determine the mixing method of the microbial agent based on the fertilizer particle parameters and the microbial agent characteristic parameters; S8: Mix the microbial agent and the high-tower compound fertilizer according to the microbial agent mixing method, and continue to perform the high-tower compound fertilizer preparation steps.

2. The method for preparing high-tower compound fertilizer with added biological agents according to claim 1, characterized in that: The high tower compound fertilizer preparation steps include: Step S101: raw material preparation; Step S102: mixing raw materials; Step S103: granulation; Step S104: drying; Step S105: cooling; Step S106: screening and grading; Step S107: packaging and storage.

3. The method for preparing high-tower compound fertilizer with added biological agents according to claim 2, characterized in that: The fertilizer characteristic parameters include fertilizer component parameters, raw material ratio parameters and fertilizer use parameters; the fertilizer component parameters are the raw material types of the high-tower compound fertilizer; the raw material ratio parameters are the mass ratio of each raw material in the high-tower compound fertilizer; the fertilizer use parameters include target crops and soil types; the target crops are the target of the high-tower compound fertilizer; the soil type is the type of soil when the target crop grows; The preparation process temperature includes granulation temperature, drying temperature and cooling temperature; The method for predicting the preparation process temperature comprises: Different digital labels are set for different raw material types, target crops and soil types, and fertilizer component parameters and fertilizer use parameters are converted into corresponding digital labels, which are marked as raw material labels, crop labels and soil labels respectively; the temperature adjustment range is obtained, and the temperature adjustment range includes a granulation temperature range, a drying temperature range and a cooling temperature range; a value is randomly selected from each range in the temperature adjustment range to construct a test set, and a total of b test sets are constructed, and different digital labels are set for each test set, and marked as a set label; the raw material label, crop label, soil label and raw material proportion parameter are used as analysis data, and the analysis data is input into the trained temperature prediction model to predict the corresponding set label, and the corresponding preparation process temperature is obtained according to the predicted set label.

4. The method for preparing high-tower compound fertilizer with added biological agents according to claim 3, characterized in that: The method for determining the characteristic parameters of the microbial agent comprises: Step S401: Preset initialization temperature T max , minimum temperature T min , cooling coefficient δ and maximum number of iterations ξ, and let the current temperature T = T max ; Step S402: preset m groups of microbial agent characteristic parameters, where m is an integer greater than 1; randomly set a feasible solution χ, where the feasible solution χ is the microbial agent characteristic parameter, and the range of the feasible solution χ is the m groups of microbial agent characteristic parameters; Step S403: determining a fitness function; The expression of fitness function is: f = pc; where f is fitness and pc is matching degree; Step S404: Calculate the fitness f corresponding to the feasible solution χ; take the feasible solution χ as the current point, perform random perturbations in the neighborhood of the current point, obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′; Step S405: Calculate the fitness difference f″; if the fitness difference f″>0, set χ=χ′; if the fitness difference f″≤0, calculate the probability p′, and set χ=χ′ according to the probability p′; Step S406: looping steps S404 to S405 until the number of loops reaches the maximum number of iterations ξ, the loop ends; let the current temperature T = T×δ; let the maximum number of iterations ξ = ξ×δ; Step S407: loop through steps S404 to S406 until the current temperature T < T min When , the loop ends, and the bacterial agent characteristic parameters corresponding to the feasible solution χ are obtained.

5. The method for preparing high-tower compound fertilizer with added biological agents according to claim 4, characterized in that: The microbial agent characteristic parameters include microbial agent component parameters and component content parameters; the microbial agent component parameters are the types of bacteria in the microbial agent; the component content parameters are the content corresponding to each type of bacteria in the microbial agent; In step S403, the method for obtaining the matching degree is: taking the inoculant characteristic parameters, analysis data and preparation process temperature corresponding to the feasible solution χ as test data; inputting the test data into the trained matching prediction model to predict the corresponding matching degree; the training process of the matching prediction model is consistent with the training process of the temperature prediction model, and both are deep neural network models; In step S405, the expression of the fitness difference f″ is f″=f′-f; the expression of the probability p′ is: p′=e T ; In the formula, e is a natural constant.

6. The method for preparing high-tower compound fertilizer with added biological agents according to claim 5, characterized in that: The particle image is an image of high-tower compound fertilizer particles during the preparation process of high-tower compound fertilizer; the fertilizer particle parameters include particle size and particle shape; The step of obtaining the fertilizer particle parameters comprises: Step S601: grayscale the particle image to obtain a grayscale image; Step S602: performing image segmentation on the grayscale image to segment the particle area in the grayscale image; Step S603: extracting the outline of each particle from the particle region using an outline detection algorithm; Step S604: Calculate the area of ​​each particle according to the outline of each particle and use it as the particle size; Step S605: Calculate the solidity of each particle according to the outline of each particle and use it as the particle shape.

7. The method for preparing high-tower compound fertilizer by adding biological agents according to claim 6, characterized in that: In step S602, the method for segmenting the particle area in the grayscale image is as follows: presetting a grayscale value threshold; obtaining the grayscale value of each pixel in the grayscale image, and comparing it with the grayscale value threshold respectively, marking the pixel points whose grayscale value is greater than or equal to the grayscale value threshold as particle points, and not marking the pixel points whose grayscale value is less than the grayscale value threshold; segmenting the grayscale image according to the particle points in the grayscale image to segment the particle area; In step S604, the method for calculating the area of ​​each particle is: obtaining the coordinates of the boundary points corresponding to the contour of each particle, and calculating the area of ​​each particle; the coordinates of the boundary points are the coordinates of the pixel points located on the boundary of the particle contour; the expression of the particle area is: Where S is the particle area, x i is the horizontal coordinate of the i-th boundary point, y i+1 is the ordinate of the i+1th boundary point, i∈[1,n], n is the number of boundary point coordinates; if i=n, then i+1=1; In step S605, the method for calculating the solidity of each particle is: using a convex hull algorithm to calculate the convex hull corresponding to the outline of each particle, and obtaining the vertex coordinates of the convex hull corresponding to the outline of each particle, and marking them as convex hull coordinates; calculating the area of ​​the convex hull corresponding to each particle according to the convex hull coordinates, and the calculation method of the convex hull area is consistent with the particle area; dividing the particle area of ​​each particle by the corresponding convex hull area to obtain the solidity of each particle.

8. A method for adding a microbial agent, characterized in that: The method for preparing high-tower compound fertilizer by adding biological agents according to any one of claims 1 to 7 is implemented, wherein the method for adding the agents includes setting the timing of adding the agents and determining the mixing method of the agents; The method for setting the timing of adding the microbial agent comprises: A strain-temperature mapping table is preset, and the strain-temperature mapping table includes a strain label and a temperature range corresponding to the strain label; the strain label is a digital label corresponding to the strain type, and different strain types have different corresponding digital labels; According to the characteristic parameters of the microbial agent, the corresponding strain label is obtained, and then according to the strain-temperature mapping table, the temperature range corresponding to each strain type is obtained and marked as the adaptation temperature range; each temperature in the preparation process temperature is sorted according to the sequence of the high-tower compound fertilizer preparation steps to obtain the temperature sequence, that is, the temperature sequence is granulation temperature, drying temperature and cooling temperature; each adaptation temperature range is compared with each temperature in the preparation process temperature according to the temperature sequence; the temperature in the preparation process temperature whose value is in each adaptation temperature range is marked as the adaptation temperature; If each temperature in the preparation process temperature is marked as an adaptation temperature, the timing of adding the bacterial agent is set to be before the granulation process of step S103 begins; If the drying temperature and the cooling temperature are marked as the adaptation temperature, the timing of adding the inoculum is set to before the drying process of step S104 begins; If the cooling temperature is marked as the adaptation temperature, but the drying temperature is not marked as the adaptation temperature, the timing of adding the inoculum is set to before the cooling process of step S105 begins; If each temperature in the preparation process temperature is not marked as an adaptation temperature, the timing of adding the bacterial agent is set to be before the screening and classification process of step S106 begins.

9. The method for adding a microbial agent according to claim 8, characterized in that: The step of determining the mixing method of the microbial agent comprises: Step S701: establishing a fuzzy set, dividing each fertilizer particle parameter and bacterial agent characteristic parameter into multiple fuzzy sets; Step S702: The fertilizer particle parameters and the microbial agent characteristic parameters are converted into the membership degree of each corresponding fuzzy set through fuzzification technology; fuzzification is the process of converting precise numerical values ​​into the membership degree corresponding to the fuzzy set; Step S703: define fuzzy rules; Step S704: matching the fuzzified fertilizer particle parameters and microbial agent characteristic parameters with the fuzzy rules, performing fuzzy reasoning, and obtaining fuzzy reasoning results, where the fuzzy reasoning results are the membership degrees corresponding to each microbial agent mixing method; Step S705: Defuzzify the fuzzy reasoning result to obtain the defuzzified result, which is the determined microbial agent mixing method; the defuzzification operation is: according to the fuzzy reasoning result, the membership corresponding to each microbial agent mixing method is compared respectively, and the mixing method corresponding to the membership with the largest numerical value is used as the microbial agent mixing method used in the preparation process of high-tower compound fertilizer.

10. A high tower compound fertilizer with added biological agents, characterized in that: It is prepared according to the method for preparing high-tower compound fertilizer with added biological bacterial agents according to any one of claims 1-7.

Images