Man-machine collaborative smart rice field cluster operation layout and dynamic scheduling method based on space-time coupling model

Abstract

The invention discloses a man-machine collaborative smart rice field cluster operation layout and dynamic scheduling method based on a space-time coupling model. The method comprises the following steps: dividing a target operation area into a plurality of standardized operation units; on the basis of a preset maximum worker circulation supply period and the operation parameters of the rice transplanters, the optimal operation row length of each sub-operation area is determined through calculation of a reverse coupling model, a peak shifting starting strategy is executed, and different starting times are set for the rice transplanters which work cooperatively in the standardized operation unit; and monitoring state information of each rice transplanter in real time, triggering a dynamic scheduling mechanism when it is predicted that supply demands of the rice transplanters conflict or operation deviates from a preset period, re-planning a supply service sequence of workers to each rice transplanter in the central supply corridor by taking global operation efficiency optimization as a target, and issuing an execution instruction. Technical support is provided for standardized construction and efficient operation of a modern unmanned farm.

Description

A Human-Machine Collaborative Smart Rice Paddy Cluster Operation Layout and Dynamic Scheduling Method Based on Spatiotemporal Coupling Model Technical Field

[0001] This invention relates to the fields of agricultural engineering and smart agriculture technology, and in particular to a human-machine collaborative smart paddy field cluster operation layout and dynamic scheduling method based on a spatiotemporal coupling model. Background Technology

[0002] With the deep integration of new-generation information technology and modern agriculture, smart agriculture has become a key approach to improving agricultural production efficiency and alleviating rural labor shortages. Rice transplanting, due to its time-sensitive nature and high precision requirements, has become a key area for the application of agricultural robotics technology. Currently, intelligent rice transplanters equipped with Global Navigation Satellite System (GNSS) and autonomous driving control units have initially achieved automatic navigation and autonomous operation in the field, significantly reducing driving intensity. However, in the process of moving from single-device automation to multi-machine cluster unmanned operation, the existing technological system still faces severe challenges in ensuring operational continuity, improving human-machine collaboration efficiency, and integrating agricultural machinery with agronomy. Specifically, while existing technologies have solved the path navigation problem for rice transplanters, they have not effectively addressed the issue of high-frequency seedling replenishment required due to the limited capacity of the seedling platform, resulting in limited operational continuity. Under the traditional "one machine, one person" or "one machine, multiple people" configuration, labor costs are too high, making it difficult to demonstrate the economic advantages of replacing human labor with machines. Furthermore, the "one person, multiple machines" model that has been attempted in some cases lacks scientific overall planning and dynamic scheduling, which can easily lead to serious operational timing conflicts. This manifests as queuing and equipment idleness caused by multiple machines simultaneously running out of seedlings, as well as physical exhaustion and response delays caused by auxiliary personnel traveling long distances between scattered fields. Consequently, the overall efficiency of multi-machine collaboration is even lower than the sum of the efficiency of single-machine operation. Furthermore, existing farmland infrastructure follows a traditional geometric layout, with irregular plots and field road networks not optimized for the logistics needs of intelligent equipment. This forces rice transplanters to make long-distance empty trips in non-standardized environments to obtain supplies, which not only increases fuel consumption and mechanical wear, but also exacerbates repeated compaction of the paddy field topsoil, damaging soil structure and affecting crop growth. At the same time, the lack of hierarchical planning of logistics routes restricts the close-range operation of large seedling transport vehicles, resulting in low efficiency in the "last mile" transfer of seedlings.

[0003] In summary, existing technologies urgently need to break through the limitations of simply increasing manpower or simply adding more machines. A system solution that deeply couples the spatial geometry of farmland with the scheduling of machine operation time should be developed. By establishing standardized farmland operation units and combining them with intelligent dynamic path planning algorithms, a single person can provide seamless, continuous, and cyclical support to multiple rice transplanters. This will reduce labor costs while maximizing the operational efficiency of agricultural machinery clusters, providing technical support for the standardized construction and efficient operation of modern unmanned farms. Summary of the Invention

[0004] To address the problem of low operational efficiency caused by irregular plots and chaotic logistics paths in traditional farmland, this invention proposes a human-machine collaborative smart paddy field cluster operation layout and dynamic scheduling method based on a spatiotemporal coupling model, which realizes an overall efficiency leap for smart farms from micro-level human-machine collaboration to macro-level cluster management.

[0005] To achieve the above objectives, this invention provides a human-machine collaborative intelligent paddy field cluster operation layout and dynamic scheduling method based on a spatiotemporal coupling model. The method includes: dividing the target operation area into several standardized operation units, each of which comprises four rectangular sub-operation areas of equal area and centrally symmetrically distributed, and a cross-shaped central supply corridor located at the intersection of the four sub-operation areas. The starting point and supply point of all rice transplanters are set at the edge of the field near the central supply corridor. Based on a preset maximum worker cycle supply period and the operation parameters of the rice transplanters, the optimal row length for each sub-operation area is determined through a reverse coupling model calculation, and a staggered start-up strategy is implemented, setting different start times for several rice transplanters cooperating within the standardized operation unit. The status information of each rice transplanter is monitored in real time. When a conflict in the supply demand of the rice transplanters is predicted or the operation deviates from the preset cycle, a dynamic scheduling mechanism is triggered. With the goal of optimizing overall operation efficiency, the supply service sequence of workers to each rice transplanter within the central supply corridor is re-planned, and execution instructions are issued.

[0006] Preferably, the standardized operating unit is formed by symmetrical division in a grid pattern, the central supply corridor is a hardened road surface for personnel to walk and light seedling transport equipment to pass through, and heavy seedling transport vehicles only unload on the external road of the standardized operating unit.

[0007] Preferably, the calculation of the reverse coupling model includes: In the formula, The maximum worker cycle time allowed for human-machine collaborative work. For the number of cooperating machines, The standard time for a worker to load seedlings onto a rice transplanter per operation. The standard time for workers to move from one supply point to the next within the central supply corridor; where the round-trip cycle of a single machine operation is included. The constraints to be satisfied are: In the formula, This is the average operating speed of the rice transplanter. This refers to the time it takes for a rice transplanter to complete one turn at the edge of the field. This is the optimal row length for the sub-job area.

[0008] Preferably, the off-peak startup strategy includes: for Each rice transplanter is numbered and started sequentially according to a preset time gradient; wherein, the preset time gradient is: In the formula, For service time points, The time interval between a worker servicing one machine and moving to the next, wherein the time interval is: In the formula, The standard time for a worker to load seedlings onto a rice transplanter per operation. The standard time taken for workers to move from one supply point to the next within the central supply corridor.

[0009] Preferably, the status information of the rice transplanter includes the real-time location, operating speed, and remaining seedling quantity of the rice transplanter; the condition for triggering the dynamic scheduling algorithm is: the difference between the predicted arrival times of any two rice transplanters to the central supply corridor is less than a preset safety threshold, or the operating delay time of a certain rice transplanter exceeds a preset warning threshold.

[0010] Preferably, the dynamic scheduling mechanism is a solution to the dynamic traveling salesman problem with soft time windows using an improved genetic algorithm, and the multi-objective cost function of the dynamic scheduling mechanism is: In the formula, Representing the Time penalty for the machine The actual time it takes for the worker to arrive at the corresponding machine. The critical moment when the machine runs out of seedlings and has to stop to wait. The cost of the distance workers travel between supply points. and All are weighting coefficients. For a multi-objective cost function, The number of cooperating machines.

[0011] Preferably, the improved genetic algorithm uses integer permutation encoding to represent the service sequence and applies tournament selection, partial mapping crossover, and exchange mutation operators for iterative optimization, outputting the optimal service sequence that minimizes the multi-objective cost function within a set time.

[0012] Preferably, the method further includes arranging and combining several standardized operating units in a matrix and constructing a hierarchical logistics network connecting each standardized operating unit; wherein the hierarchical logistics network includes at least an outer main road for heavy vehicle traffic, secondary branch roads connecting the standardized operating units and the main road, and the central supply corridor serving as the core of the internal logistics of the standardized operating units.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the human-machine collaborative smart paddy field cluster operation layout and dynamic scheduling method based on a spatiotemporal coupling model.

[0014] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the human-machine collaborative smart paddy field cluster operation layout and dynamic scheduling method based on a spatiotemporal coupling model.

[0015] Compared with the prior art, the present invention has the following advantages and technical effects: (1) The present invention constructs a modular "central radial" standardized operation unit. Through the "field" symmetrical layout and the central cross supply corridor design, the manual supply activities are restricted to the smallest central area, the ineffective transfer distance is minimized and the intensive management of seedling logistics is realized. (2) The present invention establishes a reverse coupling model between operation parameters and farmland scale, and formulates a staggered start-up strategy based on time phase difference to ensure that the round-trip operation cycle of the rice transplanter and the worker's cyclic supply cycle are precisely matched on the time axis, theoretically eliminating the idle time of the machine and realizing "zero waiting" continuous operation.

[0016] (3) To address speed fluctuations or sudden fault disturbances caused by complex farmland environments, this invention introduces a dynamic path planning mechanism based on an improved genetic algorithm. This mechanism reconstructs the worker supply service sequence in real time with the goal of achieving optimal global efficiency, endowing the system with strong anti-interference capabilities and robustness. Ultimately, through matrix replication of standard units and the construction of a hierarchical logistics network, the overall efficiency of the smart farm is elevated from micro-level human-machine collaboration to macro-level cluster management. Attached Figure Description

[0017] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings: Figure 1 is a diagram of a grid-shaped symmetrical smart paddy field layout and human-machine collaborative operation scenario according to an embodiment of the present invention; Figure 2 is a diagram of the reciprocating operation trajectory of an intelligent rice transplanter according to an embodiment of the present invention; Figure 3 is a diagram of the operation cycle and manual replenishment cycle of a single rice transplanter according to an embodiment of the present invention; Figure 4 is a diagram of staggered start-up and cyclic operation of four rice transplanters according to an embodiment of the present invention; Figure 5 is a diagram of the standard cyclic replenishment path according to an embodiment of the present invention; Figure 6 is a diagram of the dynamic global optimal path according to an embodiment of the present invention; Figure 7 is a schematic diagram of the modular matrix layout and hierarchical transportation network of a smart farm according to an embodiment of the present invention. Detailed Implementation

[0018] It should be noted that, without conflict, the embodiments and features in the embodiments of this application can be combined with each other. The following will describe this application in detail with reference to the drawings and in combination with the embodiments.

[0019] It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0020] This embodiment proposes a human-machine collaborative intelligent paddy field cluster operation layout and dynamic scheduling method based on a spatio-temporal coupling model, including: dividing the target operation area into a number of standardized operation units, where each of the standardized operation units includes four rectangular sub-operation areas with equal areas and symmetrically distributed around the center, and a cross-shaped central supply corridor located at the intersection of the four sub-operation areas. The operation starting points and supply points of all transplanters are set at the edge of the field near the central supply corridor; based on the preset maximum cycle supply period of workers and the operation parameters of the transplanters, through reverse coupling model calculation, determine the optimal operation row length of each sub-operation area, and implement a peak-shift start strategy to set different start times for several transplanters operating in coordination within the standardized operation unit; monitor the status information of each transplanter in real time. When it is predicted that the supply demand of the transplanter will conflict or the operation deviates from the preset cycle, trigger the dynamic scheduling mechanism, and with the goal of the optimal global operation efficiency, re-plan the supply service sequence of workers for each transplanter within the central supply corridor and issue an execution instruction.

[0021] Specifically, this embodiment first constructs a modular "central radiation type" standardized operation unit. Through the "field" - shaped symmetric layout and the design of the central cross supply corridor, the manual supply activities are restricted within the smallest central area, minimizing the ineffective transfer distance and realizing the intensive management of the seedling logistics. Secondly, to solve the timing conflict of machine queuing for supply in the "one person, multiple machines" mode, a reverse coupling model of operation parameters and farmland scale is established, and a peak-shift start strategy based on time phase difference is formulated to ensure that the round-trip operation cycle of the transplanter and the cycle supply period of the worker are accurately咬合 on the time axis, theoretically eliminating the machine idle time and realizing "zero waiting" continuous operation. In addition, for the speed fluctuations or sudden failure disturbances caused by the complex farmland environment, this embodiment introduces a dynamic scheduling mechanism based on an improved genetic algorithm to reconstruct the supply service sequence of workers in real time with the goal of the optimal global efficiency, endowing it with strong anti-interference ability and robustness. Finally, through the matrix replication of standard units and the construction of a hierarchical logistics network, the overall efficiency leap of the intelligent farm from micro human-machine collaboration to macro cluster management and control is realized.

[0022] It should be noted that the "咬合" in the original Chinese text seems to be a wrong or unclear expression. I translated it as "咬合" according to the literal meaning. If it has a specific correct meaning, it may need to be adjusted according to the actual situation.Furthermore, the standardized operation unit is formed by a cross-shaped symmetric division. The central supply corridor is a hardened road surface for personnel to walk and light seedling transportation equipment to pass. Heavy seedling transportation vehicles only unload goods on the external roads of the standardized operation unit.

[0023] Specifically, as shown in Figure 1, in this embodiment, a large-area operation area is discretized into several replicable standardized operation units. Each standardized operation unit is constructed as an independent geometric closed-loop system, and the specific characteristics of its internal space topology are as follows: Adopt the "cross-shaped" central symmetric division strategy. Divide a single standardized operation unit into four rectangular sub-operation areas with equal areas and congruent shapes. The four sub-operation areas are centrally symmetrically distributed about the geometric center point of the unit. This highly regular geometric fractal design eliminates the dead corners at the edges of traditional trapezoidal or polygonal fields, ensuring that the intelligent transplanter can perform full-coverage straight-line operations, and avoiding the efficiency loss caused by irregular turning from a physical basis. Secondly, construct a "cross-shaped" central hardened supply corridor. At the common intersection of the four sub-operation areas, plan and construct an operation road in the shape of a "cross". As the logistics hub of the entire unit, the road surface strength of the central supply corridor needs to meet the bearing requirements for the supply personnel to walk and light seedling transportation equipment to pass. This corridor not only physically separates the four sub-operation areas, but also serves as the only "human-machine interaction interface" in terms of function: Force all intelligent transplanters to anchor the operation starting point and seedling supply point on the inner edge of the field adjacent to the central corridor.

[0024] Based on the above layout, this embodiment establishes a "central radiation type" operation flow line, as shown in Figure 2. During the operation process, the supply personnel and seedling materials are strictly restricted within the limited range of the central supply corridor (i.e., the "static core"), while the four transplanters perform centrifugal operations from this core to the outer edge and reciprocate back (i.e., the "dynamic radiation"). This structure completely changes the traditional linear mode of "following the supply along the perimeter of the field ridge" and transforms it into an efficient "star network" supply mode. Its technical effects are as follows: On the one hand, compress the moving path of the supply workers from the perimeter of the operation area to an extremely small central radius, greatly reducing the physical consumption and ineffective transfer time of the workers; on the other hand, through the logistics classification of "heavy vehicles do not enter the field", heavy seedling transportation vehicles only unload goods on the external roads of the unit, avoiding the compaction damage to the paddy field tillage layer, and achieving the perfect unity of agricultural machinery operation and agronomic requirements.

[0025] Furthermore, simple spatial optimization is insufficient to eliminate the queuing risk in the "one person, multiple machines" mode. If multiple rice transplanters return to the central supply corridor simultaneously, peak demand exceeding manual service capacity will instantly form. After successfully establishing an intensive spatial layout, this embodiment then focuses on collaborative optimization in the time dimension, aiming to eliminate the timing conflict between the concurrent demand of multiple machines and the service capacity of a single person. To this end, this embodiment provides a precise control method for operation timing based on a spatiotemporal coupling model.

[0026] Specifically, the inverse coupling model of operating parameters and farmland scale: the geometry of traditional farmland is fixed, and the machine operating cycle... They can only passively adapt. This embodiment, through reverse design principles, limits the maximum worker cycle time allowed for human-machine collaborative work. As a hard constraint, the optimal job line length of the sub-job area is solved in reverse. . This refers to the worker completing the task. Taiwan collaborative machine (in this example) The maximum time required for continuous resupply of ( ) is calculated using the following formula: In the formula, For the number of cooperating machines, The standard time for a worker to load seedlings onto a rice transplanter per operation. The standard time for workers to move from one supply point to the next within the central supply corridor; further, as shown in Figure 3, to ensure that the machine can be serviced just in time when the seedlings are exhausted, the round-trip cycle of a single operation of the machine. The following constraints must be met: In the formula, This is the average operating speed of the rice transplanter. This refers to the time it takes for a rice transplanter to complete one turn at the edge of the field. This is the optimal row length for the sub-job area.

[0027] By setting the above inequality as an equality, the critical optimal length of the sub-work area of ​​the standardized work unit can be accurately calculated. . The determination of these parameters fundamentally locks in the operational efficiency of farmland geometry, avoiding delays in worker services due to excessively long plots or wasteful machine runs due to excessively short plots, and ensuring zero-wait time for human-machine collaborative operations under a theoretical closed-loop state.

[0028] Furthermore, despite the optimized geometry, if four rice transplanters start simultaneously, they will all return to the central supply corridor at the same time, instantly causing peak congestion. Therefore, a time phase difference was introduced for initial timing control.

[0029] The staggered startup strategy specifically includes: calculating the startup interval. :Will Defined as the time interval between a worker serving one machine and moving on to the next: In the formula, The standard time for a worker to load seedlings onto a rice transplanter per operation. The standard time taken for workers to move from one supply point to the next within the central supply corridor.

[0030] Gradient initiation: for Taiwanese rice transplanter Number them and start them sequentially according to the following time gradient: In the formula, For service time points, The time interval between a worker servicing one machine and moving to the next; in this embodiment, .

[0031] As shown in Figure 4, this strategy introduces a controllable temporal gradient at the initial stage of the operation, evenly distributing the supply needs of the four machines throughout the entire operation cycle on the time axis, thus ensuring their service time points. Strictly staggered The interval.

[0032] This initialization control allows workers to complete tasks as if operating on an assembly line, without running or waiting. After the service, proceed on foot. Just in The system ensures that supplies are replenished when needed, thus maintaining the continuity of the operational status and the stability of efficiency throughout the entire lifecycle of the cluster operation.

[0033] Furthermore, while the aforementioned "spatiotemporal coupling model" and "off-peak start-up strategy" can achieve perfect human-machine collaboration under ideal steady-state conditions, random disturbances are inevitable in actual agricultural production. For example, differences in water depth and mud level in different fields can cause the rice transplanter to slip, thus affecting the operating speed. Nonlinear fluctuations; or a machine needs to be temporarily stopped for troubleshooting due to a seedling needle malfunction, disrupting the preset phase balance; or workers' replenishment time is delayed due to decreased physical strength. The accumulation of these random variables can quickly disrupt the pre-set static loop, causing multiple machines to unexpectedly request supplies simultaneously, leading to system paralysis.

[0034] To address the aforementioned robustness issues, this embodiment constructs a real-time dynamic scheduling closed loop of "global perception - global decision-making - flexible execution" based on static time-series planning, and introduces a dynamic path planning mechanism based on an improved genetic algorithm (GA) to establish the system's adaptive adjustment capability.

[0035] Specifically, a global data acquisition layer is first constructed. Using a vehicle-mounted high-precision positioning module (GNSS) and photoelectric liquid level sensors, key state vectors of the four rice transplanters are acquired in real time at a high frequency (e.g., 1Hz), including instantaneous position, real-time operating speed, and the percentage of remaining seedlings. Based on this real-time data, the central control algorithm uses Kalman filtering to predict the estimated arrival time of each machine at the central supply corridor.

[0036] The system continuously monitors the cluster status. When the difference between the actual arrival time and the estimated arrival time (ETA) of any two machines is less than the safety threshold for worker operations (i.e., a timing conflict occurs), or when the lag time of a machine exceeds the warning line, the static loop is deemed to have failed, and the dynamic replanning algorithm is automatically triggered to take over the worker's path decision-making power.

[0037] This embodiment models the dynamic supply path planning problem for workers as a dynamic traveling salesman problem with a soft time window. Input the current machine coordinates. And according to Conversion of predicted remaining job time This allows us to obtain the optimal service sequence for workers to access each machine within the central supply corridor. .

[0038] To seek the global optimum in a variable environment, this embodiment constructs a multi-objective cost function with dual weights. : In the formula, Representing the Time penalty for the machine The actual time it takes for the worker to arrive at the corresponding machine. The critical moment when the machine runs out of seedlings and has to stop to wait. The cost of the distance workers travel between supply points. and All are weighting coefficients. For a multi-objective cost function, The number of cooperating machines.

[0039] This embodiment is set It clarifies that the highest scheduling principle is "ensuring continuous machine operation (reducing downtime)" over "ensuring workers' labor is saved (reducing movement)".

[0040] Furthermore, the improved genetic algorithm uses integer permutation encoding to represent the service sequence and applies tournament selection, partial mapping crossover, and exchange mutation operators for iterative optimization, outputting the optimal service sequence that minimizes the multi-objective cost function within a set time.

[0041] Specifically, for this mathematical model, this embodiment employs an improved genetic algorithm to perform a fast iterative search within the solution space: Encoding strategy: Chromosomes are generated using integer permutations. For example, chromosomes... The workers will break the clockwise cycle and serve in turn. .

[0042] Selection operator: Tournament selection is used, randomly selecting individuals from the parent population to compete, preserving fitness (i.e., ...). The highest level is used to maintain population diversity and prevent premature convergence.

[0043] Crossover operator: This operator employs partial mapping crossover to address the characteristics of sequence encoding. It guarantees the uniqueness and validity of offspring chromosome genes during the crossover process, avoiding invalid solutions obtained by repeatedly accessing the same machine.

[0044] Mutation operator: Employs exchange mutation to randomly swap two targets in the service sequence with a low probability, preventing the algorithm from getting trapped in local optima.

[0045] After rapid algorithm iteration (e.g., completing 100 generations of evolution within 500ms), the system outputs a cost function. The minimum optimal service sequence is used to send instructions to workers' wearable terminals via wireless network.

[0046] For example, as shown in Figures 5-6, when When the worker is severely delayed due to slippage, the algorithm will automatically instruct the worker to "skip". Supply points should be prioritized for areas where seedlings are about to run out. Replenish supplies, then proceed with further processing. This dynamic mechanism breaks the rigid, fixed-sequence cycle, giving the system a strong anti-interference capability and ensuring that the overall downtime of the rice transplanter cluster always approaches zero under any non-ideal working conditions, thus achieving robust control in complex farmland environments.

[0047] Furthermore, the method also includes arranging and combining several standardized operating units in a matrix and constructing a hierarchical logistics network connecting each standardized operating unit; wherein the hierarchical logistics network includes at least an outer main road for heavy vehicle traffic, secondary branch roads connecting the standardized operating units and the main road, and the central supply corridor serving as the core of the internal logistics of the standardized operating units.

[0048] Specifically, as shown in Figure 7, after optimizing the space and time within a single operation unit, this embodiment expands the vision to the entire area. Using modular design, the standardized operation units are arranged in a matrix, and combined with a hierarchical logistics network, enabling the local single-operator multi-machine collaboration efficiency to be perfectly replicated across the entire farm to achieve efficient management and control of scale cluster operations.

[0049] Specifically, this embodiment defines the aforementioned "field" - shaped standardized operation unit as the smallest basic geometric module that can be infinitely expanded. Based on the total land area and topographic features of the farm, a matrix layout plan is generated. At the logistics level, a three - level diversion road network system of "primary main road - secondary branch road - tertiary operation corridor" is constructed. The primary main road runs through the longitudinal axis of the farm and serves as the dedicated circulation channel for the seedling transport vehicle, strictly prohibited from entering the interior of the operation fields to protect the soil tillage layer; the secondary branch roads are located between the columns of the standard operation sub - unit matrix and serve as the interaction interfaces for distributing seedlings from the seedling transport vehicle to the edges of each unit; the tertiary operation corridor is the cross - shaped central area inside the standard operation sub - unit and is the high - frequency interaction area between the unit operator and the rice transplanter cluster. This hierarchical architecture not only ensures the smooth flow of macroscopic logistics but also realizes the overall efficiency leap of the smart farm from microscopic single - point operations to macroscopic overall management and control through the hierarchical division of physical space.

[0050] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a method for the layout and dynamic scheduling of a human - machine collaborative smart paddy field cluster operation based on a spatio - temporal coupling model.

[0051] This embodiment also provides a computer - readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of a method for the layout and dynamic scheduling of a human - machine collaborative smart paddy field cluster operation based on a spatio - temporal coupling model.

[0052] Above, only the preferred specific embodiments of this application are provided, but the protection scope of this application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in this application should be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A human-machine collaborative intelligent paddy field cluster operation layout and dynamic scheduling method based on a spatiotemporal coupling model, characterized in that, include: The target operation area is divided into several standardized operation units. Each standardized operation unit includes four rectangular sub-operation areas of equal area and centrally symmetrically distributed, and a cross-shaped central supply corridor located at the intersection of the four sub-operation areas. The starting point and supply point of all rice transplanters are set at the edge of the field near the central supply corridor. Based on the preset maximum worker cycle replenishment period and the rice transplanter's operating parameters, the optimal row length for each sub-operation area is determined through reverse coupling model calculation, and a staggered start-up strategy is implemented to set different start times for several rice transplanters cooperating in the standardized operation unit. The status information of each rice transplanter is monitored in real time. When it is predicted that the rice transplanter's replenishment demand will conflict or the operation will deviate from the preset cycle, a dynamic scheduling mechanism is triggered. With the goal of optimizing the overall operation efficiency, the replenishment service sequence of workers for each rice transplanter in the central replenishment corridor is replanned, and execution instructions are issued.

2. The method for human-machine collaborative intelligent paddy field cluster operation layout and dynamic scheduling based on a spatiotemporal coupling model according to claim 1, characterized in that, The standardized operating unit is formed by symmetrical division in a grid pattern. The central supply corridor is a hardened road surface used for personnel walking and light seedling transport equipment passage. Heavy seedling transport vehicles only unload on the external road of the standardized operating unit.

3. The human-machine collaborative intelligent paddy field cluster operation layout and dynamic scheduling method based on a spatiotemporal coupling model according to claim 2, characterized in that, The calculation of the reverse coupling model includes: In the formula, The maximum worker cycle time allowed for human-machine collaborative work. For the number of cooperating machines, The standard time for a worker to load seedlings onto a rice transplanter per operation. The standard time for workers to move from one supply point to the next within the central supply corridor; where the round-trip cycle of a single machine operation is included. The constraints to be satisfied are: In the formula, This is the average operating speed of the rice transplanter. This refers to the time it takes for a rice transplanter to complete one turn at the edge of the field. This is the optimal row length for the sub-job area.

4. The method for human-machine collaborative intelligent paddy field cluster operation layout and dynamic scheduling based on a spatiotemporal coupling model according to claim 1, characterized in that, The staggered startup strategy includes: for Each rice transplanter is numbered and started sequentially according to a preset time gradient; wherein, the preset time gradient is: In the formula, For service time points, The time interval between a worker servicing one machine and moving to the next, wherein the time interval is: In the formula, The standard time for a worker to load seedlings onto a rice transplanter per operation. The standard time taken for workers to move from one supply point to the next within the central supply corridor.

5. The human-machine collaborative intelligent paddy field cluster operation layout and dynamic scheduling method based on a spatiotemporal coupling model according to claim 1, characterized in that, The status information of the rice transplanter includes the real-time location, operating speed and remaining seedling quantity of the rice transplanter; the conditions for triggering the dynamic scheduling algorithm are: the difference between the predicted arrival times of any two rice transplanters to the central supply corridor is less than a preset safety threshold, or the operation lag time of a certain rice transplanter exceeds a preset warning threshold.

6. The method for human-machine collaborative intelligent paddy field cluster operation layout and dynamic scheduling based on a spatiotemporal coupling model according to claim 1, characterized in that, The dynamic scheduling mechanism solves the dynamic traveling salesman problem with a soft time window using an improved genetic algorithm. The multi-objective cost function of the dynamic scheduling mechanism is: In the formula, Representing the Time penalty for the machine The actual time it takes for the worker to arrive at the corresponding machine. The critical moment when the machine runs out of seedlings and has to stop to wait. The cost of the distance workers travel between supply points. and All are weighting coefficients. For a multi-objective cost function, The number of cooperating machines.

7. The human-machine collaborative intelligent paddy field cluster operation layout and dynamic scheduling method based on a spatiotemporal coupling model according to claim 6, characterized in that, The improved genetic algorithm uses integer permutation encoding to represent the service sequence and applies tournament selection, partial mapping crossover, and exchange mutation operators for iterative optimization, outputting the optimal service sequence that minimizes the multi-objective cost function within a set time.

8. The method for human-machine collaborative intelligent paddy field cluster operation layout and dynamic scheduling based on a spatiotemporal coupling model according to claim 1, characterized in that, The method further includes arranging and combining several standardized operating units in a matrix and constructing a hierarchical logistics network connecting each standardized operating unit; wherein the hierarchical logistics network includes at least an outer main road for heavy vehicle traffic, secondary branch roads connecting the standardized operating units and the main road, and the central supply corridor serving as the internal logistics core of the standardized operating units.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 8.

Images