Straw utilization and livestock and poultry breeding capacity matching intelligent planning system and method

Abstract

The present application relates to the technical field of agricultural resource utilization, in particular to an intelligent planning system and method for matching straw utilization and livestock and poultry breeding capacity, which comprises a data sensing module, a space-time dynamic matching module, a consumption verification module, a dynamic re-planning control module and a digital twin interaction module.The data sensing module dynamically calculates the collectable amount of straw and the processing capacity gap of the farm; the space-time dynamic matching module constructs a space-time accessibility matrix with transportation cost, carbon emission cost and time decay factor as constraints, and generates a Pareto optimal matching scheme set using a multi-objective evolutionary algorithm; the consumption verification module performs environmental feasibility screening on the scheme based on the soil nitrogen and phosphorus capacity; the dynamic re-planning control module monitors disturbance events and triggers incremental re-planning; and the digital twin interaction module realizes visual display and scheduling instruction generation of the scheme.The present application realizes dynamic two-way matching of straw supply and breeding demand, and improves resource utilization efficiency and system robustness.

Description

Technical Field

[0001] This invention relates to the field of agricultural resource utilization technology, and more specifically, to an intelligent planning system and method for matching straw utilization with livestock and poultry breeding capacity. Background Technology

[0002] Air pollution from open burning of straw and eutrophication of water bodies caused by direct discharge of livestock manure have become prominent issues restricting the green development of agriculture. There is a natural complementary relationship between the resource utilization of straw (such as for feed, energy, and fertilizer) and the treatment of livestock manure: straw can be used as feed, raw material for biogas fermentation, or a conditioner for manure composting, while the surplus capacity of livestock manure treatment facilities can also accommodate straw resources from surrounding areas. Therefore, achieving optimal matching between straw utilization and livestock production capacity has significant environmental and economic benefits. Thus, it is necessary to design an intelligent planning system and method for matching straw utilization with livestock production capacity.

[0003] The existing technology has the following main drawbacks:

[0004] 1. Existing technologies mostly estimate the amount of straw that can be collected based on planting area and fixed coefficients from statistical yearbooks, ignoring the significant impact of real-time factors such as rainfall, humidity, and storage time on the actual collectability of straw. This results in planning being based on "false supply" and scheduling failures during the execution phase due to "having accounts but no materials".

[0005] 2. Existing technologies treat farms only as demanders, ignoring the potential surplus capacity of farm processing facilities. This fails to achieve two-way matching between farms and between farms and straw resources, resulting in resource mismatch and idle processing capacity.

[0006] 3. Existing technologies use a static planning model. Once extreme weather, disease outbreaks, or market price fluctuations occur, the original plan immediately becomes invalid, making real-time adjustments and incremental replanning impossible, resulting in poor system robustness.

[0007] 4. Existing technologies only consider economic costs and do not take into account carbon emissions during transportation and the soil nitrogen and phosphorus absorption capacity after manure is returned to the field. As a result, although the planning scheme is economically feasible, it actually causes high carbon emissions or non-point source pollution of farmland. Summary of the Invention

[0008] The purpose of this invention is to provide an intelligent planning system and method for matching straw utilization with livestock and poultry breeding capacity, so as to solve the problems mentioned in the background art.

[0009] To achieve the above objectives, the present invention aims to provide an intelligent planning system for matching straw utilization with livestock and poultry breeding capacity, comprising: a data sensing module, used to obtain the theoretical straw yield of each plot, dynamically calculate the straw collectability coefficient of each plot by accessing meteorological data, multiply the theoretical yield by the collectability coefficient to obtain the collectable amount of straw, and simultaneously collect the daily manure output and remaining capacity of the treatment facilities of each farm to calculate the treatment capacity gap of each farm.

[0010] The spatiotemporal dynamic matching module is used to construct a spatiotemporal accessibility matrix with the available straw as the upper limit constraint for supply and the processing capacity gap as the upper limit constraint for demand. The matrix is ​​constrained by transportation costs, carbon emission costs, and time decay factors. Based on this matrix, the module dynamically pairs straw supply nodes with livestock demand nodes to generate a Pareto optimal matching scheme set.

[0011] The disposal verification module is used to receive the Pareto optimal matching scheme set, obtain the soil background data of the destination of the manure or biogas slurry generated in the matching scheme, calculate the cumulative nitrogen and phosphorus disposal amount of the application plot, and remove the matching scheme from the ranking of the Pareto optimal scheme set if it exceeds the preset threshold.

[0012] The dynamic replanning control module is used to monitor disturbance events. When the disturbance intensity exceeds a set threshold, it interrupts the current execution plan and triggers the spatiotemporal dynamic matching module to perform incremental replanning.

[0013] The digital twin interaction module is used to visualize the Pareto optimal matching scheme set in the form of a three-dimensional geographic information map and generate an execution list containing operation paths, operation time windows, and equipment scheduling instructions.

[0014] As a further improvement to this technical solution, the straw collectability coefficient for any plot of land is calculated using the following formula:

[0015]

[0016] in, Indicates the straw collectability coefficient. Indicates the theoretical baseline collectable coefficients. Indicates the meteorological dynamic correction factor. This represents the material's aging decay factor.

[0017] As a further improvement to this technical solution, the specific implementation method of the processing capacity gap is as follows: For any farm, based on the farm's daily manure production, the rated processing capacity of the treatment facility, and the currently occupied processing volume, the rated processing capacity of the treatment facility is subtracted from the currently occupied processing volume to obtain the remaining capacity of the treatment facility, and the daily manure production is subtracted from the remaining capacity of the treatment facility to obtain the processing capacity gap.

[0018] When the processing capacity gap is positive, the farm is determined to be in a state of insufficient processing capacity. The positive value indicates the farm's need for external processing of straw or manure.

[0019] When the processing capacity gap is negative, the farm is determined to be in a state of surplus processing capacity. The absolute value of the negative value represents the amount of processing capacity that the farm can provide to external parties.

[0020] When the processing capacity gap is zero, the farm is determined to be in a state of balanced processing capacity and will not participate in the current matching as a backup node.

[0021] As a further improvement to this technical solution, the time decay factor is dynamically determined based on the elapsed time after the straw supply node is harvested and the utilization path type adopted by the breeding node.

[0022] The utilization path types include at least feed path, energy path and fertilizer path, and each utilization path type corresponds to a preset shelf life and maximum effective days.

[0023] When the elapsed time after harvesting at the straw supply node is less than or equal to the shelf life in days for that utilization path type, the time decay factor is set to 1, indicating that the straw is fully compatible with that utilization path.

[0024] When the elapsed time after the harvest of straw at the supply node is greater than the shelf life but less than or equal to the maximum effective number of days, the time decay factor decreases linearly from 1 to 0 as the elapsed time increases.

[0025] When the elapsed time after the harvest of the straw supply node is greater than the maximum effective number of days, the time decay factor is set to 0, indicating that the straw does not match the utilization path, and the corresponding spatiotemporal reachability matrix element is set to unreachable.

[0026] As a further improvement to this technical solution, the spatiotemporal reachability matrix is ​​specifically implemented as follows:

[0027] Obtain the location coordinates, collectable amount of straw, and harvesting time of each straw supply node, as well as the location coordinates, processing capacity gap, and utilization path type of each breeding node.

[0028] For each pair of straw supply nodes and breeding nodes, the actual transportation distance between them is calculated based on road conditions, and the transportation cost is calculated based on the actual transportation distance, the amount of straw that can be collected, and the unit transportation cost.

[0029] The transportation carbon emission cost is calculated based on the actual transportation distance, the amount of straw that can be collected, the unit transportation carbon emission factor, and the carbon price.

[0030] Based on the harvesting time of the straw supply node and the utilization path type of the breeding node, the time decay factor is determined and multiplied by the preset time penalty coefficient to obtain the time decay penalty term.

[0031] The combined accessibility cost of the pair is obtained by adding the transportation cost, transportation carbon emission cost, and time decay penalty.

[0032] The comprehensive accessibility costs of each pair are arranged according to the correspondence between supply nodes and breeding nodes to form a spatiotemporal accessibility matrix; among them, the pairings that are determined to be unreachable are marked as infinity in the matrix.

[0033] As a further improvement to this technical solution, the spatiotemporal dynamic matching engine uses a multi-objective evolutionary algorithm to dynamically pair based on the spatiotemporal reachability matrix as follows: each matching scheme is encoded as an integer vector of the breeding node number assigned to each straw supply node, an initial population is randomly generated, and multiple optimization objectives are used, including comprehensive transportation cost, carbon emission cost and straw utilization rate. Schemes that violate the constraint of the gap in the processing capacity of the breeding nodes are penalized. The population is stratified through non-dominated sorting, and iterative evolution is performed through selection, crossover and mutation until convergence. Then, all matching schemes in the first non-dominated layer are output as the Pareto optimal matching scheme set.

[0034] As a further improvement to this technical solution, the cumulative nitrogen and phosphorus absorption of the application plot is specifically achieved by: obtaining the soil background data of the plot where the manure or biogas slurry is destined in the matching scheme, wherein the soil background data includes soil type, soil nitrogen and phosphorus background capacity and plot area.

[0035] Based on the total amount of manure or biogas slurry and its preset average nitrogen and phosphorus concentrations, calculate the proposed additional nitrogen and phosphorus input for this plot of land.

[0036] The historically recorded cumulative nitrogen and phosphorus inputs of the site are added to the proposed new nitrogen and phosphorus inputs to obtain the updated cumulative nitrogen and phosphorus inputs.

[0037] The updated nitrogen input is divided by the product of the soil nitrogen background capacity and the plot area to obtain the cumulative nitrogen absorption; the updated phosphorus input is divided by the product of the soil phosphorus background capacity and the plot area to obtain the cumulative phosphorus absorption.

[0038] When the cumulative nitrogen or phosphorus consumption exceeds a preset threshold, the environmental load of the matching scheme is determined to be excessive, and it is removed from the Pareto optimal matching scheme set or its ranking is reduced.

[0039] As a further improvement to this technical solution, the disturbance events include: sudden weather changes causing the straw moisture content to exceed a preset moisture content threshold, disease outbreaks in livestock farms causing a decrease in the number of livestock exceeding a preset proportion, and fluctuations in the market price of straw or manure exceeding a preset range; the disturbance intensity is the ratio of the quantitative indicator corresponding to the disturbance event to the preset threshold.

[0040] The second aspect of the present invention provides an intelligent planning method for matching straw utilization with livestock and poultry breeding capacity, including: S1, data sensing, used to obtain the theoretical yield of straw in each plot, dynamically calculate the straw collection coefficient of each plot by accessing meteorological data, and multiply the theoretical yield by the collection coefficient to obtain the straw collection amount; at the same time, collecting the daily output of manure and wastewater of each farm and the remaining capacity of the treatment facilities, and calculating the treatment capacity gap of each farm.

[0041] S2. Spatiotemporal dynamic matching is used to construct a spatiotemporal accessibility matrix with the available straw as the upper limit constraint for supply and the processing capacity gap as the upper limit constraint for demand. The matrix is ​​used to dynamically match straw supply nodes with livestock demand nodes to generate a Pareto optimal matching scheme set.

[0042] S3. Absorption Verification: This function receives the Pareto optimal matching scheme set, obtains the soil background data of the destination of the manure or biogas slurry generated in the matching scheme, calculates the cumulative nitrogen and phosphorus absorption of the application plot, and removes the matching scheme from the Pareto optimal scheme set if it exceeds a preset threshold.

[0043] S4. Dynamic replanning control is used to monitor disturbance events. When the disturbance intensity exceeds a set threshold, the current execution plan is interrupted, and the spatiotemporal dynamic matching module is triggered to perform incremental replanning.

[0044] S5. Digital twin interaction, used to visualize the Pareto optimal matching scheme set in the form of a three-dimensional geographic information map, and generate an execution list containing operation paths, operation time windows, and equipment scheduling instructions.

[0045] As a further improvement to this technical solution, the construction of the spatiotemporal accessibility matrix in step S2 further includes: dynamically calculating the economic transportation radius from each straw supply node to each livestock demand node using road condition and vehicle load data; if the actual transportation distance exceeds the economic transportation radius, then the corresponding spatiotemporal accessibility matrix element is set to infinity.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0047] 1. By introducing a meteorological dynamic correction factor and a material time-effect decay factor, the straw collectability coefficient is calculated in real time, and the theoretical yield is transformed into a dynamic supply ceiling, which solves the problem of "false supply" caused by static estimation and improves the feasibility of the planning scheme.

[0048] 2. By calculating the real-time processing capacity gap of the farm, the farm can be dynamically determined as either a demander or a supplier, enabling the farm to both receive straw and manure and export surplus processing capacity. This creates a new two-way matching model between straw and livestock, improving resource utilization efficiency.

[0049] 3. By taking transportation costs, carbon emission costs, and time decay factors as constraints, the feasibility of pairing each straw supply node with a breeding node is comprehensively evaluated. Through dynamic calculation of the economic transportation radius, economically unreasonable pairings are eliminated, ensuring the economic feasibility and environmental friendliness of the planning scheme.

[0050] 4. The dynamic replanning control module monitors disturbances such as weather, disease, and prices in real time. When the disturbance intensity exceeds the threshold, incremental replanning is automatically triggered, and only the affected nodes are locally adjusted. This ensures the system's rapid response, reduces computational overhead, and significantly improves the system's robustness and adaptability.

[0051] 5. Based on soil baseline data and historical fertilization records, the cumulative nitrogen and phosphorus absorption of manure-returned fields is calculated. Schemes exceeding environmental thresholds are eliminated or downgraded, preventing non-point source pollution in farmland from the source and achieving a balance between economic and environmental benefits. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a schematic diagram of the system structure connection of the present invention.

[0054] Figure 2 This is a schematic diagram of the implementation steps of the method of the present invention. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] Example: Please refer to Figure 1 As shown, an intelligent planning system for matching straw utilization with livestock and poultry breeding capacity is provided. This system includes: a data sensing module, used to acquire the theoretical straw yield of each plot based on multi-source remote sensing imagery, dynamically calculate the straw collectability coefficient of each plot by integrating meteorological data, and multiply the theoretical yield by the collectability coefficient to obtain the collectable straw quantity, thus representing the dynamic supply ceiling of each straw supply node; simultaneously, based on IoT sensors, it collects the daily manure output and remaining capacity of treatment facilities of each farm, and dynamically calculates the treatment capacity gap of each farm based on the difference between the two, thus representing the dynamic demand direction and magnitude of each breeding node; a positive gap indicates a demand state of insufficient treatment capacity at the farm, while a negative gap indicates a supply state of surplus treatment capacity at the farm.

[0057] In one specific embodiment, the straw collectability coefficient for any plot of land is calculated using the following formula:

[0058]

[0059] in, Indicates the straw collectability coefficient. This represents the theoretical baseline collectable coefficient, ranging from 0.65 to 0.85, preset according to different crop types (rice, wheat, corn) and harvesting methods (mechanical / manual). This represents a meteorological dynamic correction factor, ranging from 0.4 to 1.0, reflecting the impact of rainfall and humidity on straw collectability. This represents the material's aging degradation factor. Its value ranges from 0.5 to 1.0, reflecting the impact of prolonged storage time after straw harvesting on its usability due to mold and nutrient loss.

[0060]

[0061] in, Indicates the rainfall correction factor. Indicates the humidity correction factor;

[0062]

[0063] in, This represents the cumulative rainfall after harvest (unit: mm), obtained through access to a meteorological API. This represents the first threshold, with a recommended value of 10mm. Values ​​below this are considered to have no significant impact. This represents the second threshold, with a recommended value of 50mm. Beyond this value, collectability drops to its lowest level. This represents the attenuation coefficient; a value of 0.0125 is recommended. (That is, for every 10mm increase in rainfall, the coefficient decreases by 0.125). This represents the minimum value; a value of 0.5 is recommended.

[0064]

[0065] in, This represents the average relative humidity (in %) after harvest, calculated as a daily average. This represents the baseline humidity; a value of 65% is recommended (the upper limit of suitable humidity for collection). This represents the humidity sensitivity coefficient, and a value of 0.015 is recommended.

[0066]

[0067] in, This indicates the elapsed time (in days) since the straw was harvested, starting from the harvest date identified by remote sensing imagery. Indicates the half-life point. This indicates a control parameter that controls the decay rate.

[0068] In one specific embodiment, the processing capacity gap is specifically implemented as follows: for any farm, based on the farm's daily manure production, the rated processing capacity of the treatment facility, and the currently occupied processing volume, the rated processing capacity of the treatment facility is subtracted from the currently occupied processing volume to obtain the remaining capacity of the treatment facility, and the daily manure production is subtracted from the remaining capacity of the treatment facility to obtain the processing capacity gap.

[0069] When the processing capacity gap is positive, the farm is determined to be in a state of insufficient processing capacity. The positive value indicates the farm's need for external processing of straw or manure.

[0070] When the processing capacity gap is negative, the farm is determined to be in a state of surplus processing capacity. The absolute value of the negative value represents the amount of processing capacity that the farm can provide to external parties.

[0071] When the processing capacity gap is zero, the farm is determined to be in a state of balanced processing capacity and will not participate in the current matching as a backup node.

[0072]

[0073] in, This indicates a processing capacity gap. This indicates the daily output of manure from the farm. Indicates the remaining capacity of the processing facility. This indicates the farm's pre-set safety buffer capacity;

[0074]

[0075] in, Indicates the rated processing capacity of the treatment facility. This indicates the current processing capacity.

[0076] The spatiotemporal dynamic matching module is used to construct a spatiotemporal accessibility matrix with the collectable amount of straw as the upper limit constraint for supply and the processing capacity gap as the upper limit constraint for demand. This matrix is ​​constrained by transportation costs, carbon emission costs, and a time decay factor. Based on this matrix, a multi-objective evolutionary algorithm is used to dynamically pair straw supply nodes with livestock demand nodes, generating a Pareto optimal matching solution set. The time decay factor is determined as a function of the material properties of straw changing over time.

[0077] The straw supply nodes here correspond to various plots of land, and each node has attributes such as location coordinates and the amount of straw that can be collected. The livestock demand nodes correspond to various farms, and each node has attributes such as location coordinates and processing capacity gap (positive gap is the demand side, and negative gap is the supply side).

[0078] In one specific embodiment, the time decay factor is dynamically determined based on the elapsed time after the straw supply node is harvested and the utilization path type adopted by the breeding node.

[0079] The utilization path types include at least feed path, energy path and fertilizer path, and each utilization path type corresponds to a preset shelf life and maximum effective days.

[0080] When the elapsed time after harvesting at the straw supply node is less than or equal to the shelf life in days for that utilization path type, the time decay factor is set to 1, indicating that the straw is fully compatible with that utilization path.

[0081] When the elapsed time after the harvest of straw at the supply node is greater than the shelf life but less than or equal to the maximum effective number of days, the time decay factor decreases linearly from 1 to 0 as the elapsed time increases.

[0082] When the elapsed time after the harvest of the straw supply node is greater than the maximum effective number of days, the time decay factor is set to 0, indicating that the straw does not match the utilization path, and the corresponding spatiotemporal reachability matrix element is set to unreachable.

[0083]

[0084] in, Indicates the shelf life (number of days when fully usable), for example, 7 days for feed, 20 days for energy, and 30 days for fertilizer; This indicates the maximum number of valid days. Once exceeded, it cannot be used. For example, 15 days for feed, 60 days for energy, and 90 days for fertilizer.

[0085] In one specific embodiment, the spatiotemporal reachability matrix is ​​implemented as follows:

[0086] Obtain the location coordinates, collectable amount of straw, and harvesting time of each straw supply node, as well as the location coordinates, processing capacity gap, and utilization path type of each breeding node.

[0087] For each pair of straw supply nodes and breeding nodes, the actual transportation distance between them is calculated based on road conditions, and the transportation cost is calculated based on the actual transportation distance, the amount of straw that can be collected, and the unit transportation cost.

[0088] The transportation carbon emission cost is calculated based on the actual transportation distance, the amount of straw that can be collected, the unit transportation carbon emission factor, and the carbon price.

[0089] Based on the harvesting time of the straw supply node and the utilization path type of the livestock breeding node, a time decay factor is determined and multiplied by a preset time penalty coefficient to obtain a time decay penalty term. Specifically, when the harvesting time exceeds the maximum effective number of days corresponding to the utilization path type, the time decay factor is zero, and the pairing is directly determined to be unreachable.

[0090] The combined accessibility cost of the pair is obtained by adding the transportation cost, transportation carbon emission cost, and time decay penalty.

[0091] The comprehensive accessibility costs of each pair are arranged according to the correspondence between supply nodes and breeding nodes to form a spatiotemporal accessibility matrix; among them, the pairings that are determined to be unreachable are marked as infinity in the matrix.

[0092] Assume the system has a total of Each straw supply node (each plot) and For each breeding node (each breeding farm), the spatiotemporal reachability matrix is... It is A matrix, where each element Indicates the first The straw supply node and the first Feasibility and overall cost of matching between individual breeding nodes.

[0093]

[0094] in, Indicates from node To the node Transportation costs, Indicates from node To the node The cost of carbon emissions from transportation This represents the time decay penalty term (based on the time decay factor).

[0095]

[0096] in, This represents the actual transport distance (in kilometers), calculated based on traffic APIs (such as Gaode / Baidu Maps), and is not a straight-line distance. Represents a node The amount of straw that can be collected (in tons) is used as the transport load. This represents the unit transportation cost (yuan / ton·km), which can be dynamically adjusted based on vehicle type and fuel price.

[0097]

[0098] in, Indicates carbon emission factor per unit of transportation ( ), Indicates carbon price ( (This can be adjusted dynamically according to carbon market conditions.)

[0099]

[0100] in, This represents the time penalty factor (in yuan), used to quantify time decay as a cost.

[0101] In one specific embodiment, the spatiotemporal dynamic matching engine uses a multi-objective evolutionary algorithm to dynamically pair up based on the spatiotemporal reachability matrix as follows: each matching scheme is encoded as an integer vector of the breeding node number assigned to each straw supply node, an initial population is randomly generated, and multiple optimization objectives are used, including comprehensive transportation cost, carbon emission cost and straw utilization rate. Schemes that violate the constraint of the gap in the processing capacity of the breeding nodes are penalized. The population is stratified through non-dominated sorting, and iterative evolution is carried out through selection, crossover and mutation until convergence. All matching schemes in the first non-dominated layer are output as the Pareto optimal matching scheme set.

[0102] The disposal verification module is used to receive the Pareto optimal matching scheme set, obtain the soil background data of the destination of the manure or biogas slurry generated in the matching scheme, calculate the cumulative nitrogen and phosphorus disposal amount of the application plot, and remove the matching scheme from the ranking of the Pareto optimal scheme set if it exceeds the preset threshold.

[0103] In one specific embodiment, the cumulative nitrogen and phosphorus absorption of the application plot is specifically achieved by: obtaining the soil background data of the plot to which the manure or biogas slurry is destined in the matching scheme, wherein the soil background data includes soil type, soil nitrogen and phosphorus background capacity and plot area.

[0104] Based on the total amount of manure or biogas slurry and its preset average nitrogen and phosphorus concentrations, calculate the proposed additional nitrogen and phosphorus input for this plot of land.

[0105] The historically recorded cumulative nitrogen and phosphorus inputs of the site are added to the proposed new nitrogen and phosphorus inputs to obtain the updated cumulative nitrogen and phosphorus inputs.

[0106] The updated nitrogen input is divided by the product of the soil nitrogen background capacity and the plot area to obtain the cumulative nitrogen absorption; the updated phosphorus input is divided by the product of the soil phosphorus background capacity and the plot area to obtain the cumulative phosphorus absorption.

[0107] When the cumulative nitrogen or phosphorus consumption exceeds a preset threshold, the environmental load of the matching scheme is determined to be excessive, and it is removed from the Pareto optimal matching scheme set or its ranking is reduced.

[0108] Formula for calculating cumulative nitrogen absorption:

[0109]

[0110] Formula for calculating cumulative phosphorus consumption:

[0111]

[0112] in, This indicates the cumulative amount of nitrogen absorbed. This indicates the soil nitrogen background capacity of the plot, expressed in kilograms per acre. This indicates the cumulative amount of phosphorus consumed. This indicates the soil phosphorus background capacity of the plot, expressed in kilograms per acre. This indicates the area of ​​the land parcel, in mu (a Chinese unit of area, approximately 0.165 acres). , These represent the proposed new nitrogen and phosphorus inputs calculated based on the total amount of manure or biogas slurry and its preset nitrogen and phosphorus concentrations, respectively. , These represent the historical cumulative nitrogen and phosphorus inputs of the land parcel, respectively.

[0113] The nitrogen input is calculated by multiplying the total amount of manure or biogas slurry allocated to the plot in the matching scheme by a preset average nitrogen concentration. Specifically, the system obtains the volume or weight of manure or biogas slurry to be applied to the plot from the matching scheme, multiplies it by the typical nitrogen content of that type of manure (e.g., 0.5% nitrogen content for pig manure and 0.3% nitrogen content for biogas slurry), and thus obtains the proposed additional nitrogen input. This nitrogen content can be dynamically obtained from a table based on the source of the manure (pig, cattle, chicken) and the pretreatment method (solid-liquid separation, anaerobic fermentation).

[0114] The phosphorus concentration is calculated by multiplying the total amount of manure or biogas slurry allocated to the plot in the matching scheme by a preset average phosphorus concentration. For example, pig manure has a phosphorus content of approximately 0.3%, and biogas slurry has a phosphorus content of approximately 0.1%. The system dynamically selects the corresponding phosphorus content for calculation based on the source of the manure and the pretreatment method. Similarly, this value is used for subsequent assessment of cumulative phosphorus consumption.

[0115] like ≤1 and If the value is ≤1, then the cumulative nitrogen and phosphorus consumption of the plot has not exceeded the standard, and the matching scheme is feasible.

[0116] like 1 or If the value is greater than 1, it is considered to be out of range, and the matching scheme should be eliminated or its ranking lowered.

[0117] The dynamic replanning control module is used to monitor disturbance events. When the disturbance intensity exceeds a set threshold, it interrupts the current execution plan and triggers the spatiotemporal dynamic matching module to perform incremental replanning.

[0118] In one specific embodiment, the disturbance events include: sudden weather changes causing the straw moisture content to exceed a preset moisture content threshold, disease outbreaks in livestock farms causing a decrease in the number of livestock exceeding a preset proportion, and fluctuations in the market price of straw or manure exceeding a preset range; the disturbance intensity is the ratio of the quantitative indicator corresponding to the disturbance event to the preset threshold.

[0119] The digital twin interaction module is used to visualize the Pareto optimal matching scheme set in the form of a three-dimensional geographic information map and generate an execution list containing operation paths, operation time windows, and equipment scheduling instructions.

[0120] See Figure 2 As shown, an intelligent planning method for matching straw utilization with livestock and poultry breeding capacity is provided, including: S1, data sensing, used to obtain the theoretical straw yield of each plot, dynamically calculate the straw collection coefficient of each plot by accessing meteorological data, and multiply the theoretical yield by the collection coefficient to obtain the straw collection amount; at the same time, the daily output of manure and wastewater of each farm and the remaining capacity of the treatment facilities are collected to calculate the treatment capacity gap of each farm.

[0121] S2. Spatiotemporal dynamic matching is used to construct a spatiotemporal accessibility matrix with the available straw as the upper limit constraint for supply and the processing capacity gap as the upper limit constraint for demand. The matrix is ​​used to dynamically match straw supply nodes with livestock demand nodes to generate a Pareto optimal matching scheme set.

[0122] S3. Absorption Verification: This function receives the Pareto optimal matching scheme set, obtains the soil background data of the destination of the manure or biogas slurry generated in the matching scheme, calculates the cumulative nitrogen and phosphorus absorption of the application plot, and removes the matching scheme from the Pareto optimal scheme set if it exceeds a preset threshold.

[0123] S4. Dynamic replanning control is used to monitor disturbance events. When the disturbance intensity exceeds a set threshold, the current execution plan is interrupted, and the spatiotemporal dynamic matching module is triggered to perform incremental replanning.

[0124] S5. Digital twin interaction, used to visualize the Pareto optimal matching scheme set in the form of a three-dimensional geographic information map, and generate an execution list containing operation paths, operation time windows, and equipment scheduling instructions.

[0125] In one specific embodiment, the construction of the spatiotemporal accessibility matrix in step S2 further includes: dynamically calculating the economic transportation radius from each straw supply node to each livestock demand node using road condition and vehicle load data; if the actual transportation distance exceeds the economic transportation radius, then setting the corresponding spatiotemporal accessibility matrix element to infinity.

[0126]

[0127] in, Indicates the economic transportation radius. This indicates the current market price per ton of straw. Indicates the straw at the breeding stage Utilization rate (value range 0~1, determined according to the utilization path). Indicates breeding nodes Cost per unit of straw processed (yuan / ton) The benchmark transportation cost (yuan / ton·km) refers to the unit transportation cost under ideal road conditions and standard load. This represents the congestion sensitivity coefficient (a preset constant, such as 0.05). Indicates from node To the node The real-time traffic congestion index (value range 0~1, obtained from navigation API, 0 indicates smooth traffic, 1 indicates severe congestion).

[0128] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention.

Claims

1. An intelligent planning system for matching straw utilization with livestock and poultry breeding capacity, characterized in that, include: The data sensing module is used to obtain the theoretical yield of straw in each plot, dynamically calculate the straw collection coefficient of each plot by integrating meteorological data, and multiply the theoretical yield by the collection coefficient to obtain the collectable amount of straw. At the same time, it collects the daily output of manure and sewage from each farm and the remaining capacity of the treatment facilities to calculate the treatment capacity gap of each farm. The spatiotemporal dynamic matching module is used to construct a spatiotemporal accessibility matrix with the available straw as the upper limit constraint for supply and the processing capacity gap as the upper limit constraint for demand, and with transportation cost, carbon emission cost and time decay factor as constraints. Based on this matrix, the module dynamically pairs straw supply nodes with livestock demand nodes to generate a Pareto optimal matching scheme set. The disposal verification module is used to receive the Pareto optimal matching scheme set, obtain the soil background data of the destination of the manure or biogas slurry generated in the matching scheme, calculate the cumulative nitrogen and phosphorus disposal amount of the application plot, and remove the matching scheme from the Pareto optimal scheme set if it exceeds the preset threshold. The dynamic replanning control module is used to monitor disturbance events. When the disturbance intensity exceeds a set threshold, it interrupts the current execution plan and triggers the spatiotemporal dynamic matching module to perform incremental replanning. The digital twin interaction module is used to visualize the Pareto optimal matching scheme set in the form of a three-dimensional geographic information map and generate an execution list containing operation paths, operation time windows, and equipment scheduling instructions.

2. The intelligent planning system for matching straw utilization with livestock and poultry breeding capacity according to claim 1, characterized in that: For any given plot of land, the straw collectability coefficient is calculated using the following formula: in, Indicates the straw collectability coefficient. Indicates the theoretical baseline collectable coefficients. Indicates the meteorological dynamic correction factor. This represents the material's aging decay factor.

3. The intelligent planning system for matching straw utilization with livestock and poultry breeding capacity according to claim 1, characterized in that: The specific method to address the aforementioned processing capacity gap is as follows: For any farm, based on the farm's daily manure production, the rated processing capacity of the treatment facility, and the currently occupied processing volume, the remaining capacity of the treatment facility is obtained by subtracting the currently occupied processing volume from the rated processing capacity of the treatment facility, and the processing capacity gap is obtained by subtracting the remaining capacity of the treatment facility from the daily manure production. When the processing capacity gap is positive, it is determined that the farm is in a state of insufficient processing capacity. The positive value represents the amount of straw or manure that the farm needs to receive from outside for processing. When the processing capacity gap is negative, the farm is determined to be in a state of surplus supply of processing capacity. The absolute value of the negative value represents the amount of processing capacity that the farm can provide to the outside world. When the processing capacity gap is zero, the farm is determined to be in a state of balanced processing capacity and will not participate in the current matching as a backup node.

4. The intelligent planning system for matching straw utilization with livestock and poultry breeding capacity according to claim 1, characterized in that: The time decay factor is dynamically determined based on the elapsed time after the straw supply node is harvested and the utilization path type adopted by the breeding node. The utilization path types include at least feed path, energy path and fertilizer path, and each utilization path type corresponds to a preset shelf life and maximum effective days; When the elapsed time after the harvest of the straw supply node is less than or equal to the shelf life in days of the utilization path type, the time decay factor is set to 1, indicating that the straw is fully compatible with the utilization path. When the elapsed time after the harvest of straw at the supply node is greater than the shelf life days but less than or equal to the maximum effective days, the time decay factor decreases linearly from 1 to 0 as the elapsed time increases. When the elapsed time after the harvest of the straw supply node is greater than the maximum effective number of days, the time decay factor is set to 0, indicating that the straw does not match the utilization path, and the corresponding spatiotemporal reachability matrix element is set to unreachable.

5. The intelligent planning system for matching straw utilization with livestock and poultry breeding capacity according to claim 1, characterized in that: The spatiotemporal reachability matrix is ​​specifically implemented as follows: Obtain the location coordinates, collectable amount of straw, and harvesting time of each straw supply node, as well as the location coordinates, processing capacity gap, and utilization path type of each breeding node; For each pair of straw supply nodes and breeding nodes, the actual transportation distance between them is calculated based on road conditions, and the transportation cost is calculated based on the actual transportation distance, the amount of straw that can be collected, and the unit transportation cost. The transportation carbon emission cost is calculated based on the actual transportation distance, the amount of straw that can be collected, the unit transportation carbon emission factor, and the carbon price. Based on the harvesting time of the straw supply node and the utilization path type of the breeding node, the time decay factor is determined and multiplied by the preset time penalty coefficient to obtain the time decay penalty term. The combined accessibility cost of the pair is obtained by adding the transportation cost, transportation carbon emission cost, and time decay penalty. The comprehensive accessibility costs of each pair are arranged according to the correspondence between supply nodes and breeding nodes to form a spatiotemporal accessibility matrix; among them, the pairings that are determined to be unreachable are marked as infinity in the matrix.

6. The intelligent planning system for matching straw utilization with livestock and poultry breeding capacity according to claim 1, characterized in that: The specific method of the spatiotemporal dynamic matching engine based on the spatiotemporal reachability matrix and using a multi-objective evolutionary algorithm for dynamic pairing is as follows: each matching scheme is encoded as an integer vector of the breeding node number assigned to each straw supply node, an initial population is randomly generated, and comprehensive transportation cost, carbon emission cost and straw utilization rate are used as multiple optimization objectives. Schemes that violate the constraint of the gap in the processing capacity of the breeding nodes are penalized. The population is stratified through non-dominated sorting, and iterative evolution is carried out through selection, crossover and mutation until convergence. Then, all matching schemes in the first non-dominated layer are output as the Pareto optimal matching scheme set.

7. The intelligent planning system for matching straw utilization with livestock and poultry breeding capacity according to claim 1, characterized in that: The specific method for achieving the cumulative nitrogen and phosphorus absorption of the application plot is as follows: Obtain soil background data for the land parcels where manure or biogas slurry is destined in the matching scheme. The soil background data includes soil type, soil nitrogen and phosphorus background capacity, and land parcel area. Calculate the proposed increase in nitrogen and phosphorus input for this plot of land based on the total amount of manure or biogas slurry and its preset average nitrogen and phosphorus concentrations. The historically recorded cumulative nitrogen and phosphorus inputs of the plot are added to the proposed new nitrogen and phosphorus inputs to obtain the updated cumulative nitrogen and phosphorus inputs. The updated nitrogen input is divided by the product of the soil nitrogen background capacity and the plot area to obtain the cumulative nitrogen absorption; the updated phosphorus input is divided by the product of the soil phosphorus background capacity and the plot area to obtain the cumulative phosphorus absorption. When the cumulative nitrogen or phosphorus consumption exceeds a preset threshold, the environmental load of the matching scheme is determined to be excessive, and it is removed from the Pareto optimal matching scheme set or its ranking is reduced.

8. The intelligent planning system for matching straw utilization with livestock and poultry breeding capacity according to claim 1, characterized in that: The disturbance events include: sudden weather changes causing the straw moisture content to exceed a preset moisture content threshold, disease outbreaks in livestock farms causing a decrease in the number of livestock exceeding a preset proportion, and fluctuations in the market price of straw or manure exceeding a preset range; the disturbance intensity is the ratio of the quantitative indicator corresponding to the disturbance event to the preset threshold.

9. A method for implementing an intelligent planning system for matching straw utilization with livestock and poultry breeding capacity as described in any one of claims 1-8, characterized in that: include: S1. Data sensing is used to obtain the theoretical yield of straw in each plot, dynamically calculate the straw collection coefficient of each plot by accessing meteorological data, and multiply the theoretical yield by the collection coefficient to obtain the straw collection amount; at the same time, the daily output of manure and sewage of each farm and the remaining capacity of the treatment facilities are collected to calculate the treatment capacity gap of each farm. S2. Spatiotemporal dynamic matching is used to construct a spatiotemporal accessibility matrix with the available straw as the upper limit of supply and the processing capacity gap as the upper limit of demand, and with transportation cost, carbon emission cost and time decay factor as constraints. Based on this matrix, straw supply nodes and breeding demand nodes are dynamically matched to generate a Pareto optimal matching scheme set. S3, Disposal Verification, is used to receive the Pareto optimal matching scheme set, obtain the soil background data of the destination of the manure or biogas slurry generated in the matching scheme, calculate the cumulative nitrogen and phosphorus disposal amount of the application plot, and remove the matching scheme from the Pareto optimal scheme set if it exceeds the preset threshold. S4. Dynamic replanning control is used to monitor disturbance events. When the disturbance intensity exceeds a set threshold, the current execution plan is interrupted, and the spatiotemporal dynamic matching module is triggered to perform incremental replanning. S5. Digital twin interaction, used to visualize the Pareto optimal matching scheme set in the form of a three-dimensional geographic information map, and generate an execution list containing operation paths, operation time windows, and equipment scheduling instructions.

10. The intelligent planning method for matching straw utilization with livestock and poultry breeding capacity according to any one of claims 9, characterized in that: The construction of the spatiotemporal accessibility matrix in step S2 further includes: dynamically calculating the economic transportation radius from each straw supply node to each livestock demand node using road condition and vehicle load data; if the actual transportation distance exceeds the economic transportation radius, then the corresponding spatiotemporal accessibility matrix element is set to infinity.

Images