Mixed fertilizer production process parameter optimization management method and system based on big data

Abstract

The invention discloses a mixed fertilizer production process parameter optimization management method and system based on big data, and relates to the technical field of process optimization. Comprising the steps of soil data acquisition, climate data acquisition, climate data prediction, soil fertility runaway ability data acquisition, crop classification, target area soil fertility demand data acquisition, market feedback data collection and optimization of a mixed fertilizer production process. The process optimization method comprises the following steps: analyzing target area soil data and target area climate data to obtain a formula adjustment direction; a formula element adjusting formula is used, the proportion of various elements in the formula is calculated, the proportion of the elements in the adjusted formula is analyzed, and the raw material mixing parameter adjusting direction is obtained; and calculating the numerical value of each parameter during raw material mixing by using a raw material mixing parameter adjustment formula. According to the invention, the existing formula can be accurately optimized, and a more accurate and effective compound fertilizer formula is formulated, so that the compound fertilizer is more suitable for crops in a target area.

Description

Technical Field

[0001] The present invention relates to the technical field of process optimization, and in particular to a method and system for optimizing management of process parameters in mixed fertilizer production based on big data. Background Art

[0002] Mixed fertilizer is obtained by mechanically mixing several single fertilizers, or mixing a single fertilizer with a binary or ternary compound fertilizer. Sometimes some fillers can be added to improve the physical and chemical properties of the fertilizer. For example, to prevent excessive acidification of mixed fertilizers made of ammonium nitrate and ordinary supercalcium phosphate, some lime can be added to neutralize excess soil acidity to create more favorable conditions for crop growth.

[0003] The application publication number is CN118644108A, which is an organic fertilizer low-carbon adaptability production management system and method. The system includes: an organic fertilizer information input module, which is configured to obtain organic fertilizer production related information in response to a user's input action; wherein the organic fertilizer production related information includes organic fertilizer information, equipment information, transportation information and fossil fuel information; a carbon emission assessment module, which is configured to perform carbon emission boundary accounting on the organic fertilizer production related information, generate accounting gas types and accounting energy consumption types as accounting results, and perform carbon emission assessment according to the accounting results to obtain a carbon emission assessment result. result; wherein the carbon emission assessment result includes gaseous carbon emissions, non-gaseous carbon emissions and transportation carbon emissions; the standard adaptability analysis module is configured to establish a first constraint based on production demand according to the production demand information of the target organic fertilizer production task, establish a second constraint based on the carbon emission rate and a third constraint based on the total carbon emissions according to the local carbon emission requirements, take the carbon emission assessment result of the target organic fertilizer production task as the state, take the production parameters in the target organic fertilizer production task as the strategy, adopt the reinforcement learning algorithm for iterative training, and obtain the optimal production operation of the target organic fertilizer production task.

[0004] The growth and development of crops require a variety of nutrients. Most of the chemical fertilizers we usually buy contain only one or two elements. For example, urea, ammonia water, ammonium carbonate, etc. are very single nitrogen fertilizers, and potassium chloride is also a very single potassium fertilizer. Only a few compound fertilizers contain multiple nutrients. At the same time, most of the existing land has been cultivated for many years. What is consumed in the soil is not only the fertility, but also various trace elements and changes in the pH value of the soil. These changes will cause the soil to change. Blindly supplementing fertility cannot help the soil recover as before. Therefore, there are mixed fertilizers specifically for the soil in the target area. The mixed fertilizer will adjust the production process according to the regular test data of the soil in the target area, mainly based on the soil in the target area. Regular soil test data is used to adjust the production formula. Although mixed fertilizers have improved the pertinence and effectiveness of fertilizers to a certain extent, they still have certain limitations. Specifically, the formula adjustment of mixed fertilizers mainly depends on soil test data, while ignoring the influence of other environmental factors. Introducing big data technology into the formulation of fertilizer formulas, through big data collection and analysis of multi-source data, including climate, soil test data and market feedback data, can more comprehensively understand the environmental conditions for crop growth, thereby formulating more accurate and effective fertilizer formulas. In addition, when optimizing the existing compound fertilizer process, the optimization of the raw material mixing parameters in the process is often neglected, resulting in uneven mixing or too long mixing time, increased energy consumption and production costs, etc. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for optimizing the management of process parameters of mixed fertilizer production based on big data to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for optimizing and managing process parameters of mixed fertilizer production based on big data, the method comprising:

[0007] Soil data collection, using recent and historical soil data for the target area;

[0008] Climate data collection: collect real-time and historical climate data of the target area;

[0009] Climate data prediction: based on the real-time climate data and historical climate data of the target area, using climate prediction calculation methods, obtain the climate data of the target area at a preset time;

[0010] Obtaining soil fertility storage capacity data, based on the climate data of the target area at a preset time and the soil data of the target area, using a soil fertility storage capacity calculation method, to obtain the soil fertility retention capacity data of the target area at the preset time;

[0011] Crop classification: using the growth fertility requirement calculation method to obtain the growth fertility requirements of various crops, and classify crops with similar growth fertility requirements into one category. Categorizing various crops facilitates the design of corresponding mixed fertilizer production formulas;

[0012] Obtain soil fertility demand data of the target area, based on the fertility demand data of the preset classified crops, using the soil fertility demand calculation method to obtain the soil fertility demand data of the preset classified crops in the target area;

[0013] Market feedback data collection: collect customer feedback data and crop suitability data, and use the weight calculation method based on the market feedback data to obtain the corresponding process optimization weight;

[0014] The mixed fertilizer production process is optimized, and the process optimization method steps are as follows:

[0015] L1: Analyze the soil data and climate data of the target area to obtain the direction of formula adjustment;

[0016] L2: Use the formula element adjustment formula to calculate the ratio of various elements in the formula. The formula element adjustment formula is as follows:

[0017]

[0018] Where: Fj is the adjusted fertilizer amount of formula element n, Fn is the original fertilizer amount of formula element n calculated based on soil fertility demand data, Wcust is the weight of customer feedback data, Δcust is the adjustment coefficient of customer feedback data for formula element n, Wcrop is the weight of crop adaptability data, Δcrop is the adjustment coefficient of crop adaptability data for formula element n, and the amount of elements in the formula is adjusted according to the calculation results to increase the yield of crops;

[0019] L3: Analyze the proportion of elements in the adjusted formula to obtain the adjustment direction of raw material mixing parameters;

[0020] L4: Use the raw material mixing parameter adjustment formula to calculate the values ​​of various parameters when mixing raw materials. The raw material mixing parameter adjustment formula is as follows:

[0021]

[0022] Where: N a is the adjusted mixing equipment parameter, N b is the basic parameter, βF is the parameter adjustment coefficient, ΔF is the change in the formula element, and F t The total amount of formula elements is calculated, and the parameters of the raw material mixing equipment are adjusted according to the calculation results to keep the production equipment in the best operating state.

[0023] The climate prediction calculation method comprises the following steps:

[0024] Step 1: Obtain the original climate data at time t;

[0025] Step 2: Obtain the original climate data at time t-1;

[0026] Step 3: Get the intercept term;

[0027] Step 4: Get the regression coefficient;

[0028] Step 5: Get the error value;

[0029] Step 6: Calculate using the climate prediction formula. The climate prediction formula is as follows:

[0030]

[0031] Among them: Δyt is the differential climate data at time t, yt is the original climate data at time t, yt-1 is the soil data of the original climate data area at time t-1;

[0032]

[0033] Where: ŷ is the predicted value of the overall climate conditions in the next season, β 0 is the intercept term, β 1 , β 2 , ..., β n is the regression coefficient, Δy t is the climate data after difference at time t, E is the error value, and the climate forecast result of the preset time in the target area is obtained.

[0034] The climate prediction calculation method comprises the following steps:

[0035] Step 1: Obtain the original climate data at time t;

[0036] Step 2: Obtain the original climate data at time t-1;

[0037] Step 3: Get the intercept term;

[0038] Step 4: Get the regression coefficient;

[0039] Step 5: Calculate using the climate prediction formula. The climate prediction formula is as follows:

[0040]

[0041] Among them: Δyt is the differential climate data at time t, yt is the original climate data at time t, yt-1 is the soil data of the original climate data area at time t-1;

[0042]

[0043] Where: ŷ is the predicted value of the overall climate conditions in the next season, β 0 is the intercept term β 1 , β 2 , ..., β n is the regression coefficient, Δy t The climate data after the difference of time t is used to obtain the climate forecast result of the preset time in the target area.

[0044] The soil fertility storage capacity calculation method comprises the following steps:

[0045] Step 1: Obtain the initial fertilizer element content of the soil before fertilization;

[0046] Step 2: Obtain the proportion of fertilizer element loss caused by climate change;

[0047] Step 3: Get the intercept term;

[0048] Step 4: Get the regression coefficient;

[0049] Step 5: Calculate using the soil fertility storage capacity data calculation formula. The soil fertility storage capacity data calculation formula is as follows:

[0050]

[0051] Where: N r Represents the fertilizer element content remaining in the soil after fertilization, N i represents the initial fertilizer element content of the soil before fertilization, λR represents the proportional function of fertilizer element loss caused by climate change, and ηF represents the fertilizer element utilization efficiency function, and the soil fertility retention capacity data is obtained.

[0052] The method for calculating the growth fertility requirement comprises the following steps:

[0053] Step 1: Obtain the fertility requirement of crop i;

[0054] Step 2: Obtain the actual fertility of crop i;

[0055] Step 3: Obtain the maximum value of fertility requirements of all crops;

[0056] Step 4: Obtain the minimum fertility requirements of all crops;

[0057] Step 5: Calculate using the growth fertility requirement calculation formula. The growth fertility requirement calculation formula is as follows:

[0058]

[0059] Where: C i is the classification of crop i, F i is the fertility requirement of crop i, F r is the actual fertility of crop i, F max is the maximum fertility requirement of all crops, F min is the minimum value of fertility requirement of all crops, and R is the representative value of fertility requirement of crop type i;

[0060] Crops with similar growth fertility requirements are grouped together, and various crops are classified to facilitate the design of corresponding mixed fertilizer production formulas.

[0061] The soil fertility requirement calculation method comprises the following steps:

[0062] Step 1: Obtain the fertilizer utilization coefficient of nutrient n;

[0063] Step 2: Obtain the demand of crops for nutrient n;

[0064] Step 3: Obtain the retention content of nutrient N in the soil;

[0065] Step 4: Obtain the loss of nutrient n in the soil;

[0066] Step 5: Calculate the soil fertility demand data of the target area based on the soil fertility demand calculation formula and the planting requirements of the preset classified crops. The soil fertility demand calculation formula is as follows:

[0067]

[0068] Among them: F n is the amount of fertilizer to be added, n represents the type of nutrient, F d is the fertilizer utilization coefficient of nutrient n, R is the demand of crops for nutrient n, S is the retention content of nutrient n in the soil, S l is the loss of nutrient n from the soil;

[0069] The nutrient requirements for planting preset classified crops in the target area are calculated, and the soil fertility requirement data for planting preset classified crops in the target area are obtained by repeated calculation.

[0070] The weight calculation method comprises the following steps:

[0071] Step 1: Obtain quality scores of customer feedback data;

[0072] Step 2: Obtain the timeliness of customer feedback data;

[0073] Step 3: Obtain the total quality score of all considered factors;

[0074] Step 4: Obtain the maximum timeliness value among all the factors considered;

[0075] Step 5: Calculate using the customer feedback data weight calculation formula. The customer feedback data weight calculation formula is as follows:

[0076]

[0077] Where: W cust is the weight of customer feedback data, Q cust Score the quality of customer feedback data, T cust To ensure the timeliness of customer feedback data, Q t The total quality score of all the factors considered, T max is the maximum timeliness value among all the factors considered.

[0078] The weight calculation method comprises the following steps:

[0079] Step 1: Obtain the nutrient adaptability score of crops;

[0080] Step 2: Obtain the economic value score of crops;

[0081] Step 3: Obtain the sum of all crop nutrient adaptability scores;

[0082] Step 4: Obtain the maximum economic value of all crops;

[0083] Step 5: Calculate using the crop adaptability data weight calculation formula. The crop adaptability data weight calculation formula is as follows:

[0084]

[0085] Where: W crop is the weight of crop adaptability data, A crop Score the nutrient adaptability of crops, E crop Score the economic value of crops, A total is the sum of all crop nutrient adaptability scores, E max It has the highest economic value among all crops.

[0086] Compared with the prior art, the present invention has the following beneficial effects:

[0087] The method and system for optimizing the production process parameters of compound fertilizers based on big data can obtain soil data and climate data of the target area through big data, so as to have a more comprehensive understanding of the environmental conditions for the growth of crops, use the formula element adjustment formula to calculate the proportion of various elements in the formula, accurately optimize the existing formula, and formulate a more accurate and effective compound fertilizer formula, so that the compound fertilizer is more suitable for the crops in the target area.

[0088] By analyzing the proportions of various elements in the adjusted formula, the adjustment direction of the raw material mixing parameters is obtained. The raw material mixing parameter adjustment formula is used to calculate the values ​​of various parameters when mixing raw materials. According to the calculation results, the parameters of the raw material mixing equipment are adjusted to keep the mixing equipment in the best operating state, avoid problems such as uneven raw material mixing or excessive mixing time, and reduce production energy consumption and production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 It is a schematic diagram of the data collection principle structure of the present invention;

[0090] Figure 2 It is a schematic diagram of the process optimization principle structure of the present invention;

[0091] Figure 3 It is a schematic diagram of the soil fertility loss principle structure of the present invention;

[0092] Figure 4 This is a schematic diagram of the principle structure of the climate prediction data of the present invention;

[0093] Figure 5 This is a schematic diagram of the principle structure of soil fertility retention in the present invention;

[0094] Figure 6 This is a schematic diagram of the principle structure of the crop classification of the present invention;

[0095] Figure 7 It is a schematic diagram of the structure of the recipe data adjustment principle of the present invention. DETAILED DESCRIPTION

[0096] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0097] In the present application, for ease of understanding, the method steps used do not need to be executed in the order of the steps in this embodiment during actual operation. In other embodiments, these steps may be performed simultaneously or in a different order.

[0098] like Figure 1-Figure 7 As shown, the present invention provides a technical solution: a method for optimizing and managing process parameters of mixed fertilizer production based on big data, the method comprising:

[0099] Soil data collection, using recent and historical soil data for the target area;

[0100] Climate data collection: collect real-time and historical climate data of the target area;

[0101] Climate data prediction: based on the real-time climate data and historical climate data of the target area, using climate prediction calculation methods, obtain the climate data of the target area at a preset time;

[0102] Obtaining soil fertility storage capacity data, based on the climate data of the target area at a preset time and the soil data of the target area, using a soil fertility storage capacity calculation method, to obtain the soil fertility retention capacity data of the target area at the preset time;

[0103] Crop classification: using the growth fertility requirement calculation method to obtain the growth fertility requirements of various crops, and classify crops with similar growth fertility requirements into one category. Categorizing various crops facilitates the design of corresponding mixed fertilizer production formulas;

[0104] Obtain soil fertility demand data of the target area, based on the fertility demand data of the preset classified crops, using the soil fertility demand calculation method to obtain the soil fertility demand data of the preset classified crops in the target area;

[0105] Market feedback data collection: collect customer feedback data and crop suitability data, and use the weight calculation method based on the market feedback data to obtain the corresponding process optimization weight;

[0106] The mixed fertilizer production process is optimized, and the process optimization method steps are as follows:

[0107] L1: Analyze the soil data and climate data of the target area to obtain the direction of formula adjustment;

[0108] L2: Use the formula element adjustment formula to calculate the ratio of various elements in the formula. The formula element adjustment formula is as follows:

[0109]

[0110] Among them: F j is the fertilizer amount of the adjusted formula element n, F n is the fertilizer amount of element n in the original formula calculated based on soil fertility requirement data, W cust is the weight of customer feedback data, Δcust is the adjustment coefficient of customer feedback data to formula element n, W crop is the weight of crop adaptability data, Δcrop is the adjustment coefficient of crop adaptability data to formula element n, and the number of elements in the formula is adjusted according to the calculation results to increase the yield of crops;

[0111] It should be noted that the weight of customer feedback data is a common and effective method to set weights and adjust formulas based on customer feedback data. It has applications in many fields, including but not limited to food science, the cosmetics industry, and fertilizer manufacturing in agriculture. The weight of crop adaptability data is a common and scientific method to set weights and adjust fertilizer formulas based on crop adaptability data by collecting data on crops in target areas. Especially in precision agriculture and sustainable agricultural practices, this method can optimize the use of fertilizers based on the needs of specific crops, soil conditions, and environmental factors, thereby increasing crop yields, improving crop quality, and reducing negative impacts on the environment.

[0112] Bring in data:

[0113] W crop =60;

[0114] W cust =76.5;

[0115] F n =48;

[0116] Δcust = 0.1 (indicates that customer feedback data recommends a 10% increase in the original formula);

[0117] Δcrop=0.05 (indicates that the crop adaptability data recommends a 5% increase in the original formula);

[0118] get:

[0119] F j =48×(1+76.5×0.1+60×0.05);

[0120] =48×(1+7.65+3);

[0121] =48×11.65;

[0122] =559.2;

[0123] Therefore, the amount of fertilizer for the adjusted formula element n is 559.2 units;

[0124] L3: Analyze the proportion of elements in the adjusted formula to obtain the adjustment direction of raw material mixing parameters;

[0125] L4: Use the raw material mixing parameter adjustment formula to calculate the values ​​of various parameters when mixing raw materials. The raw material mixing parameter adjustment formula is as follows:

[0126]

[0127] Where: N a is the adjusted mixing equipment parameter, Nb is the basic parameter, βF is the parameter adjustment coefficient, ΔF is the change in the formula element, and F t The total amount of formula elements is calculated, and the parameters of the raw material mixing equipment are adjusted according to the calculation results to keep the production equipment in the best operating state.

[0128] Substitute the data:

[0129] Nb=100 (assuming the base parameter is 100);

[0130] βF=0.5 (assuming the parameter adjustment coefficient is 0.5);

[0131] ΔF=10 (assuming the formula element changes by 10 units);

[0132] Ft=100 (assuming the total amount of recipe elements is 100 units, which means we are considering a recipe change of an overall or specific proportion);

[0133] Substituting these data into the formula, we get:

[0134] Na=100×(1+10010×0.5);

[0135] =100×(1+0.1×0.5);

[0136] =100×(1+0.05);

[0137] =100×1.05;

[0138] =105;

[0139] Therefore, the adjusted mixing equipment parameter Na is 105.

[0140] The climate prediction calculation method is as follows:

[0141] Step 1: Obtain the original climate data at time t;

[0142] Step 2: Obtain the original climate data at time t-1;

[0143] Step 3: Get the intercept term;

[0144] Step 4: Get the regression coefficient;

[0145] Step 5: Get the error value;

[0146] Step 6: Calculate using the climate prediction formula. The climate prediction formula is as follows:

[0147]

[0148] Among them: Δyt is the differential climate data at time t, yt is the original climate data at time t, yt-1 is the soil data of the original climate data area at time t-1;

[0149]

[0150] Where: ŷ is the predicted value of the overall climate conditions in the next season, β 0 is the intercept term, β 1 , β 2 , ..., β n is the regression coefficient, Δy t is the climate data after difference at time t, E is the error value, and the climate forecast result of the preset time in the target area is obtained.

[0151] It should be noted that the climate system is often regarded as a near-chaotic system due to its complex nonlinear dynamic characteristics, which means that there is significant uncertainty in long-term climate forecasts (such as decades or longer). However, for seasonal forecasts on shorter time scales (such as a few months to a season), existing scientific knowledge and technical means can be used to make a certain degree of effective predictions, such as the sub-seasonal-seasonal-interannual scale integrated climate model prediction system developed by the China Meteorological Administration.

[0152] Bring in data,

[0153] β0=10;

[0154] β1=0.5;

[0155] β2=−0.2; ...;

[0157] βn=0.1;

[0158] E = 0.5;

[0159] Δy1=2;

[0160] Δy2=−1;

[0161] Δy3=0.5; ...;

[0163] Δyn=1 (this is an assumed value, just for demonstration);

[0164] but:

[0165] Ŷ=10+0.5×2+(−0.2)×(−1)+0.1×0.5+...+0.1×1+0.5;

[0166] =10+1−0.2+0.05+...+0.1+0.5;

[0167] =11.85+...+0.5;

[0168] Thus, the forecast of the overall climate conditions for the next season is obtained;

[0169] It should be noted that the forecast value is only a prediction of the overall precipitation in the target area in the next season.

[0170] The climate prediction calculation method is as follows:

[0171] Step 1: Obtain the original climate data at time t;

[0172] Step 2: Obtain the original climate data at time t-1;

[0173] Step 3: Get the intercept term;

[0174] Step 4: Get the regression coefficient;

[0175] Step 5: Calculate using the climate prediction formula. The climate prediction formula is as follows:

[0176]

[0177] Among them: Δyt is the differential climate data at time t, yt is the original climate data at time t, yt-1 is the soil data of the original climate data area at time t-1;

[0178]

[0179] Where: ŷ is the predicted value of the overall climate conditions in the next season, β 0 is the intercept term β 1 , β 2 , ..., β n is the regression coefficient, Δy t The climate data after the difference of time t is used to obtain the climate forecast result of the preset time in the target area;

[0180] Bring in data,

[0181] β0=10;

[0182] β1=0.5;

[0183] β2=−0.2; ...;

[0185] βn=0.1;

[0186] Δy1=2;

[0187] Δy2=−1;

[0188] Δy3=0.5; ...;

[0190] Δyn=1 (this is an assumed value, just for demonstration);

[0191] but:

[0192] Ŷ=10+0.5×2+(−0.2)×(−1)+0.1×0.5+...+0.1×1;

[0193] =10+1−0.2+0.05+...+0.1;

[0194] =11.85+...;

[0195] Thus, the predicted value of the overall precipitation climate conditions for the next season can be obtained.

[0196] The calculation method of soil fertility storage capacity is as follows:

[0197] Step 1: Obtain the initial fertilizer element content of the soil before fertilization;

[0198] Step 2: Obtain the proportion of fertilizer element loss caused by climate change;

[0199] Step 3: Calculate using the soil fertility storage capacity data calculation formula. The soil fertility storage capacity data calculation formula is as follows:

[0200]

[0201] Where: N r Represents the fertilizer element content remaining in the soil after fertilization, N i represents the initial fertilizer element content of the soil before fertilization, λR represents the fertilizer element loss ratio function caused by climate change, ηF represents the fertilizer element utilization efficiency function, and the soil fertility retention capacity data is obtained;

[0202] Bring in data:

[0203] N i =100 (the initial fertilizer element content of the soil before fertilization is 100 units);

[0204] λR=0.2 (the loss of fertilizer elements due to climate change is 20%);

[0205] ηF=0.8 (fertilizer element utilization efficiency is 80%);

[0206] Substituting these data into the formula, we get:

[0207] N r =100×(1−0.2)×0.8;

[0208] =100×0.8×0.8;

[0209] =64;

[0210] Get the soil fertility retention capacity data.

[0211] The calculation method of growth fertility requirements is as follows:

[0212] Step 1: Obtain the fertility requirement of crop i;

[0213] Step 2: Obtain the actual fertility of crop i;

[0214] Step 3: Obtain the maximum value of fertility requirements of all crops;

[0215] Step 4: Obtain the minimum fertility requirements of all crops;

[0216] Step 5: Calculate using the growth fertility requirement calculation formula. The growth fertility requirement calculation formula is as follows:

[0217]

[0218] Where: C i is the classification of crop i, F i is the fertility requirement of crop i, F r is the actual fertility of crop i, F max is the maximum fertility requirement of all crops, F min is the minimum value of fertility requirement of all crops, and R is the representative value of fertility requirement of crop type i;

[0219] Substitute the data:

[0220] F i =150 (the fertility requirement of crop i is 150 units);

[0221] F r =120 (the actual fertility obtained by crop i is 120 units);

[0222] F max =200 (the maximum fertility requirement of all crops is 200 units);

[0223] F min =50 (the minimum fertility requirement for all crops is 50 units);

[0224] R = {0.2, 0.5, 0.8} (assuming there are three categories, and their representative values ​​of fertility requirements are 0.2, 0.5, and 0.8 respectively);

[0225] Note: The R values ​​here are representative values. For simplicity, we can assume that these representative values ​​are relative to F. max −F min Normalized value, if not, we need to normalize R first.

[0226] First, calculate:

[0227] (F i −F r ) / (F max −F min );

[0228] = (150−120) / (200-50);

[0229] =30 / 150;

[0230] =0.2;

[0231] Then, we calculate the absolute value of the difference between each class and 0.2:

[0232] For R1=0.2: |0.2−0.2|=0;

[0233] For R2=0.5: |0.2−0.5|=0.3;

[0234] For R3=0.8: |0.2−0.8|=0.6;

[0235] Since 0 is the smallest difference, the classification of crop i is C i The category corresponding to R1=0.2;

[0236] Crops with similar growth fertility requirements are grouped together, and various crops are classified to facilitate the design of corresponding mixed fertilizer production formulas.

[0237] The soil fertility requirement calculation method is as follows:

[0238] Step 1: Obtain the fertilizer utilization coefficient of nutrient n;

[0239] Step 2: Obtain the demand of crops for nutrient n;

[0240] Step 3: Obtain the retention content of nutrient N in the soil;

[0241] Step 4: Obtain the loss of nutrient n in the soil;

[0242] Step 5: Calculate the soil fertility demand data of the target area based on the soil fertility demand calculation formula and the planting requirements of the preset classified crops. The soil fertility demand calculation formula is as follows:

[0243]

[0244] Among them: F n is the amount of fertilizer to be added, n represents the type of nutrient, F d is the fertilizer utilization coefficient of nutrient n, R is the demand of crops for nutrient n, S is the retention content of nutrient n in the soil, S l is the loss of nutrient n from the soil;

[0245] Bring in data:

[0246] For nutrients n (e.g. nitrogen):

[0247] Fd=0.6 (fertilizer utilization coefficient is 60%);

[0248] R = 200 (the crop's demand for nutrient n is 200 units);

[0249] S = 150 (the retention content of nutrient n in the soil is 150 units);

[0250] Sl = 30 (the loss of nutrient n in the soil is 30 units);

[0251] Substituting these data into the formula, we get:

[0252] F n =0.6×(200−(150−30));

[0253] =0.6×(200−120);

[0254] =0.6×80;

[0255] =48;

[0256] So, for nutrient n, the amount of fertilizer that needs to be added is 48 units.

[0257] The nutrient requirements for planting preset classified crops in the target area are calculated, and the soil fertility requirement data for planting preset classified crops in the target area are obtained by repeated calculation.

[0258] The weight calculation method is as follows:

[0259] Step 1: Obtain quality scores of customer feedback data;

[0260] Step 2: Obtain the timeliness of customer feedback data;

[0261] Step 3: Obtain the total quality score of all considered factors;

[0262] Step 4: Obtain the maximum timeliness value among all the factors considered;

[0263] Step 5: Calculate using the customer feedback data weight calculation formula. The customer feedback data weight calculation formula is as follows:

[0264]

[0265] Where: W cust is the weight of customer feedback data, Q cust Score the quality of customer feedback data, T cust To ensure the timeliness of customer feedback data, Q t The total quality score of all the factors considered, T max is the maximum timeliness value among all the factors considered.

[0266] Substitute the data:

[0267] Q cust =85 (the quality score of customer feedback data is 85 points);

[0268] T cust =0.9 (the timeliness of customer feedback data is 0.9, assuming this is a value normalized to between 0 and 1);

[0269] T max =1.0 (the maximum timeliness value among all the factors considered is 1.0, indicating the highest timeliness);

[0270] Substituting these data into the formula, we get:

[0271] W cust =1.085×0.9;

[0272] =76.5;

[0273] Therefore, the weight of customer feedback data is 76.5.

[0274] The weight calculation method is as follows:

[0275] Step 1: Obtain the nutrient adaptability score of crops;

[0276] Step 2: Obtain the economic value score of crops;

[0277] Step 3: Obtain the sum of all crop nutrient adaptability scores;

[0278] Step 4: Obtain the maximum economic value of all crops;

[0279] Step 5: Calculate using the crop adaptability data weight calculation formula. The crop adaptability data weight calculation formula is as follows:

[0280]

[0281] Where: W crop is the weight of crop adaptability data, A crop Score the nutrient adaptability of crops, E crop Score the economic value of crops, A total is the sum of all crop nutrient adaptability scores, E max It has the highest economic value among all crops.

[0282] Substitute the data:

[0283] A crop =80 (the nutrient adaptability score of crops is 80 points);

[0284] E crop =750 (the economic value of the crop is scored as 750 units, which may be some kind of currency or value measurement unit);

[0285] E max =1000 (the maximum economic value of all crops is 1000 units);

[0286] Substituting these data into the formula, we get:

[0287] W crop =80×750 / 1000;

[0288] =60;

[0289] Therefore, the weight of crop adaptability data is 60.

[0290] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.

Claims

1. A method for optimizing and managing process parameters of mixed fertilizer production based on big data, characterized in that: The method comprises: Soil data collection, using recent and historical soil data for the target area; Climate data collection: collect real-time and historical climate data of the target area; Climate data prediction: calculate the climate data of the target area at the preset time; Obtain soil fertility storage capacity data, and use calculation methods to obtain soil fertility retention capacity data for a preset time target area; Crop classification: calculate the growth fertility requirements of various crops and classify them; Obtain soil fertility requirement data of the target area, and calculate soil fertility requirement data of crops of preset classification in the target area based on the fertility requirement data of crops of preset classification; Market feedback data collection, based on which the corresponding process optimization weights are calculated; The mixed fertilizer production process is optimized, and the process optimization method steps are as follows: L1: Analyze the soil data and climate data of the target area to obtain the direction of formula adjustment; L2: Calculate the ratio of various elements in the formula. The formula for adjusting the formula elements is as follows: , where: F j is the fertilizer amount of the adjusted formula element n, F n is the fertilizer amount of element n in the original formula calculated based on soil fertility requirement data, W cust is the weight of customer feedback data, Δcust is the adjustment coefficient of customer feedback data to formula element n, W crop is the weight of crop adaptability data, Δcrop is the adjustment coefficient of crop adaptability data to formula element n; L3: Analyze the proportion of elements in the adjusted formula to obtain the adjustment direction of raw material mixing parameters; L4: Calculate the values ​​of various parameters when mixing raw materials. The raw material mixing parameter adjustment formula is as follows: , where: N a is the adjusted mixing equipment parameter, N b is the basic parameter, βF is the parameter adjustment coefficient, ΔF is the change in the formula element, and F t is the total amount of formula elements.

2. The method for optimizing the production process parameters of mixed fertilizer based on big data according to claim 1, characterized in that: The climate prediction calculation method comprises the following steps: Step 1: Obtain the original climate data at time t; Step 2: Obtain the original climate data at time t-1; Step 3: Get the intercept term; Step 4: Get the regression coefficient; Step 5: Get the error value; Step 6: Calculate using the climate prediction formula. The climate prediction formula is as follows: , where: Δyt is the differential climate data at time t, yt is the original climate data at time t, and yt-1 is the soil data of the original climate data area at time t-1; , where: ŷ is the predicted value of the overall climate conditions in the next season, β0 is the intercept term, β1, β2, ..., β n is the regression coefficient, Δy t is the climate data after difference at time t, E is the error value, and the climate forecast result of the preset time in the target area is obtained.

3. The method for optimizing the production process parameters of mixed fertilizer based on big data according to claim 1, characterized in that: The climate prediction calculation method comprises the following steps: Step 1: Obtain the original climate data at time t; Step 2: Obtain the original climate data at time t-1; Step 3: Calculate using the climate prediction formula. The climate prediction formula is as follows: , where: Δyt is the differential climate data at time t, yt is the original climate data at time t, and yt-1 is the soil data of the original climate data area at time t-1; , where: ŷ is the predicted value of the overall climate conditions in the next season, β0 is the intercept term β1, β2, ..., β n is the regression coefficient, Δy t The climate data after the difference of time t is used to obtain the climate forecast result of the target area at the preset time.

4. The method for optimizing the production process parameters of mixed fertilizer based on big data according to claim 1, characterized in that: The soil fertility storage capacity calculation method comprises the following steps: Step 1: Obtain the initial fertilizer element content of the soil before fertilization; Step 2: Obtain the proportion of fertilizer element loss caused by climate change; Step 3: Get the intercept term; Step 4: Get the regression coefficient; Step 5: Calculate using the soil fertility storage capacity data calculation formula. The soil fertility storage capacity data calculation formula is as follows: , where: N r Represents the fertilizer element content remaining in the soil after fertilization, N i represents the initial fertilizer element content of the soil before fertilization, λR represents the proportional function of fertilizer element loss caused by climate change, and ηF represents the fertilizer element utilization efficiency function, and the soil fertility retention capacity data is obtained.

5. The method for optimizing the production process parameters of mixed fertilizer based on big data according to claim 1, characterized in that: The method for calculating the growth fertility requirement comprises the following steps: Step 1: Obtain the fertility requirement of crop i; Step 2: Obtain the actual fertility of crop i; Step 3: Obtain the maximum value of fertility requirements of all crops; Step 4: Obtain the minimum fertility requirements of all crops; Step 5: Calculate using the growth fertility requirement calculation formula. The growth fertility requirement calculation formula is as follows: , where: C i is the classification of crop i, F i is the fertility requirement of crop i, F r is the actual fertility of crop i, F max is the maximum fertility requirement of all crops, F min is the minimum value of fertility requirement of all crops, and R is the representative value of fertility requirement of crop type i; Crops with similar growth fertility requirements are grouped together, and various crops are classified to facilitate the design of corresponding mixed fertilizer production formulas.

6. The method for optimizing the production process parameters of mixed fertilizer based on big data according to claim 1, characterized in that: The soil fertility requirement calculation method comprises the following steps: Step 1: Obtain the fertilizer utilization coefficient of nutrient n; Step 2: Obtain the demand of crops for nutrient n; Step 3: Obtain the retention content of nutrient N in the soil; Step 4: Obtain the loss of nutrient n in the soil; Step 5: Calculate the soil fertility demand data of the target area based on the soil fertility demand calculation formula and the planting requirements of the preset classified crops. The soil fertility demand calculation formula is as follows: , where: F n is the amount of fertilizer to be added, n represents the type of nutrient, F d is the fertilizer utilization coefficient of nutrient n, R is the demand of crops for nutrient n, S is the retention content of nutrient n in the soil, S l is the loss of nutrient n from the soil; The nutrient requirements for planting preset classified crops in the target area are calculated, and the soil fertility requirement data for planting preset classified crops in the target area are obtained by repeated calculation.

7. The method for optimizing the production process parameters of mixed fertilizer based on big data according to claim 1, characterized in that: The weight calculation method comprises the following steps: Step 1: Obtain quality scores of customer feedback data; Step 2: Obtain the timeliness of customer feedback data; Step 3: Obtain the total quality score of all considered factors; Step 4: Obtain the maximum timeliness value among all the factors considered; Step 5: Calculate using the customer feedback data weight calculation formula. The customer feedback data weight calculation formula is as follows: , where: W cust is the weight of customer feedback data, Q cust Score the quality of customer feedback data, T cust To ensure the timeliness of customer feedback data, Q t The total quality score of all the factors considered, T max is the maximum timeliness value among all the factors considered.

8. The method for optimizing the production process parameters of mixed fertilizer based on big data according to claim 1, characterized in that: The weight calculation method comprises the following steps: Step 1: Obtain the nutrient adaptability score of crops; Step 2: Obtain the economic value score of crops; Step 3: Obtain the sum of all crop nutrient adaptability scores; Step 4: Obtain the maximum economic value of all crops; Step 5: Calculate using the crop adaptability data weight calculation formula. The crop adaptability data weight calculation formula is as follows: , where: W crop is the weight of crop adaptability data, A crop Score the nutrient adaptability of crops, E crop Score the economic value of crops, A total is the sum of all crop nutrient adaptability scores, E max It has the highest economic value among all crops.

9. The big data-based optimization management system for compound fertilizer production process parameters according to claim 1, characterized in that: A method for optimizing and managing process parameters for mixed fertilizer production based on big data as described in any one of claims 1 to 8 is used.

Images