Intelligent biological irrigation system and method based on remote control

Abstract

The invention relates to the technical field of agricultural irrigation, in particular to an intelligent biological irrigation system and method based on remote control, and the system comprises a biological sensing unit, a neural computing decision engine, a driving execution unit, and a communication optimization architecture. Wherein the biological sensing unit is used for monitoring multi-modal data of plant physiological status, rhizosphere microenvironment and meteorological parameters in real time; the neural computing decision engine is used for constructing a pulse neural network, fusing a plant dimensional management system signal transduction mechanism and a multi-agent optimization algorithm, and generating a millisecond-level dynamic irrigation strategy; the driving execution unit is used for millimeter-level water quantity adjustment and pipe network self-repairing of the irrigation execution unit; the communication optimization architecture is used for seamless coverage and secure transmission of irrigation data, and meanwhile, a strategy is optimized by applying algorithms such as reinforcement learning and the like. Therefore, the problems of water resource waste, poor irrigation effect, untimely irrigation strategy adjustment and the like in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural irrigation, and in particular to an intelligent biological irrigation system and method based on remote control. Background Art

[0002] In the field of global agricultural production, irrigation has always been a key link to ensure crop growth and increase crop yields. With the advancement of science and technology, automated irrigation systems have gradually entered the field of agricultural production. Whether it is a large-scale grain-producing area or an intensive vegetable and fruit planting base, unprecedented high requirements are placed on the intelligence and precision of the irrigation system. The remote-controlled intelligent biological irrigation system can monitor multi-modal data such as plant physiological status, rhizosphere microenvironment, and meteorological parameters in real time and in all directions, and with the help of advanced intelligent analysis technology, accurate decision-making can be achieved to achieve efficient and precise irrigation.

[0003] However, traditional irrigation mostly relies on manual experience, and farmers use their intuitive judgment of crop appearance and soil moisture to decide the timing and amount of irrigation. This method lacks scientific accuracy and is prone to irrigation errors. In some farmlands that use traditional irrigation methods, water resources wasted due to over-irrigation can reach 30%-40% of the total irrigation volume each year. On the contrary, during busy farming seasons or when there is a shortage of manpower, it is easy to irrigate in a timely manner or inadequately, which affects crop growth and reduces yields. Summary of the invention

[0004] The present application provides an intelligent biological irrigation system and method based on remote control to solve the problems of water resource waste, poor irrigation effect, and untimely adjustment of irrigation strategy in the prior art.

[0005] The first aspect of the present application provides an intelligent biological irrigation system based on remote control, including: a biological sensor unit, a neural computing decision engine, a drive execution unit, and a communication architecture; wherein the biological sensor unit is used to monitor multimodal data of plant physiological state, rhizosphere microenvironment and meteorological parameters in real time; the neural computing decision engine is used to construct a pulse neural network, integrate the signal conduction mechanism of the plant vascular system and the multi-agent optimization algorithm, and generate a millisecond-level dynamic irrigation strategy; the drive execution unit is used for millimeter-level water volume regulation and pipe network self-repair of the irrigation execution unit; the communication optimization architecture is used for seamless coverage and secure transmission of irrigation data, and at the same time, algorithms such as reinforcement learning are used to optimize the strategy.

[0006] Preferably, the biosensing unit includes nanoscale plant physiological monitoring and in situ characterization of the soil microenvironment, wherein the nanoscale plant physiological monitoring is used to detect in real time the ABA concentration in the plant xylem, the organic acid composition in the root system and the turgor pressure state of the stomatal guard cells, and provide molecular-level stress warning data; the in situ characterization of the soil microenvironment is used to obtain in real time the soil moisture distribution, nutrient status and microbial community abundance, provide in situ data for soil health management, and formulate irrigation strategies.

[0007] Preferably, the neural computing decision engine includes a pulse neural network construction submodule and a bio-inspired computing architecture, wherein the pulse neural network construction submodule is used to imitate the pulse emission mechanism of biological neurons, construct a pulse neural network model, and process and analyze sensor data; the bio-inspired computing architecture is used to imitate the signal conduction mechanism of the plant vascular system, combine the memristor cross array with the pulse neural network, process biological signals, and generate dynamic irrigation strategies.

[0008] Preferably, the neural computing decision engine includes a dynamic growth model, which is used to integrate satellite remote sensing and ground sensor data, combine multi-agent systems, and coordinate optimization algorithms to predict the spatiotemporal distribution of crop water requirements.

[0009] Preferably, the neural computing decision engine further includes a pulse neural network model, and the formula of the pulse neural network model is: ; in, is the membrane time constant; is the membrane potential; is the resting potential; is the membrane resistance; is the input current; is the time derivative of the membrane potential.

[0010] Preferably, the neural computing decision engine further includes a dynamic growth model, and the formula of the dynamic growth model is: ; in, is the growth rate; is the inherent growth rate; K is the environmental carrying capacity; is the current population size.

[0011] Preferably, the driving execution unit includes a biosimulation irrigation unit and a self-repairing intelligent pipe network, wherein the biosimulation irrigation unit is used to drive the stomatal structure actuator and the magnetically controlled nanoparticle guidance technology to achieve millimeter-level root targeted irrigation; the self-repairing intelligent pipe network is used to monitor the pipe network pressure, flow and leakage status in real time, automatically trigger the repair mechanism, and extend the life of the pipe network.

[0012] Preferably, the communication optimization architecture includes a data transmission interaction engine, a network intelligent management and operation and maintenance module, and a strategy intelligent optimization feedback unit, wherein the data transmission interaction engine is used to safely and efficiently transmit and interact with multi-source data to support system collaborative operation and decision-making; the network intelligent management and operation and maintenance module is used to build and maintain the communication network topology of the intelligent biological irrigation system in real time, centrally manage network nodes, use machine learning to diagnose and predict faults, and ensure communication stability; the strategy intelligent optimization feedback unit is used to collect irrigation execution data and environmental feedback of the intelligent biological irrigation system, and use algorithms such as reinforcement learning to optimize irrigation strategies and improve irrigation efficiency.

[0013] The second aspect of the present application provides an intelligent biological irrigation method based on remote control, including: acquiring multimodal data, wherein the multimodal data includes plant physiological state, rhizosphere microenvironment and meteorological parameters; constructing a pulse neural network based on the multimodal data, and generating a dynamic irrigation strategy based on the pulse neural network fusion signal conduction mechanism and optimization algorithm; according to the dynamic irrigation strategy, performing millimeter-level water volume regulation and irrigation, automatically locating pipeline leakage points and starting backup pipelines; securely transmitting soil moisture, irrigation volume and other data after the irrigation to a decision-making platform for data coverage, and at the same time, adjusting and optimizing the strategy according to the actual irrigation effect.

[0014] The third aspect of the present application 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 program to implement an intelligent biological irrigation system based on remote control as in the above embodiment.

[0015] Therefore, this application includes the following beneficial effects: The embodiment of the present application uses a biosensor unit to collect multimodal data of plant physiology, rhizosphere microenvironment and meteorological parameters in real time, laying a solid foundation for precision irrigation; the neural computing decision engine deeply integrates pulse neural networks, plant vascular system signal transmission mechanisms and multi-agent optimization algorithms, generates dynamic irrigation strategies at the millisecond level, and accurately adapts to the water demand characteristics of crops at different growth stages; the driving execution unit realizes millimeter-level water volume regulation through stomatal structure actuators, and uses intelligent pipe network self-repair technology to reduce the risk of failure; the communication optimization architecture not only ensures data security transmission and seamless coverage, but also continuously optimizes irrigation strategies with the help of reinforcement learning algorithms; it can increase water resource utilization by more than 40%, reduce soil compaction, adapt to complex farmland environments, and reduce operation and maintenance costs. As a result, the problems of water resource waste, poor irrigation effect, and untimely adjustment of irrigation strategies in the prior art are solved.

[0016] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which: Figure 1 A schematic diagram of the structure of an intelligent biological irrigation system based on remote control provided according to an embodiment of the present application; Figure 2 A schematic diagram of a biosensor unit provided according to one embodiment of the present application; Figure 3 A schematic diagram of a neural computing decision engine provided according to one embodiment of the present application; Figure 4 A schematic diagram of a drive execution unit provided according to an embodiment of the present application; Figure 5 A schematic diagram of a communication optimization architecture provided according to an embodiment of the present application; Figure 6 A schematic diagram of a network intelligence platform system provided according to an embodiment of the present application; Figure 7 A flowchart of an intelligent biological irrigation method based on remote control provided according to an embodiment of the present application; Figure 8 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] The following describes an intelligent biological irrigation system based on remote control according to an embodiment of the present application with reference to the accompanying drawings. In response to the problem of water resource waste mentioned in the above background technology, the present application provides an intelligent biological irrigation system based on remote control, in which multimodal data of plant physiology, rhizosphere microenvironment and meteorological parameters are collected in real time through a biological sensor unit to lay a solid foundation for precision irrigation; the neural computing decision engine deeply integrates pulse neural networks, plant vascular system signal transduction mechanisms and multi-agent optimization algorithms, generates dynamic irrigation strategies at the millisecond level, and accurately adapts to the water demand characteristics of crops at different growth stages; the driving execution unit realizes millimeter-level water volume regulation through a stomatal structure actuator, and uses intelligent pipe network self-repair technology to reduce the risk of failure; the communication optimization architecture not only ensures data security transmission and seamless coverage, but also continuously optimizes irrigation strategies with the help of reinforcement learning algorithms; it can increase water resource utilization by more than 40%, reduce soil compaction, adapt to complex farmland environments, and reduce operation and maintenance costs. As a result, the problems of water resource waste, poor irrigation effect, and untimely adjustment of irrigation strategies in the prior art are solved.

[0020] Figure 1 A schematic diagram of the composition of an intelligent biological irrigation system based on remote control provided in an embodiment of the present application.

[0021] The embodiment of the present application provides an intelligent biological irrigation system based on remote control, the system 10 includes: Biosensor unit 100, neural computing decision engine 200, drive execution unit 300, communication optimization architecture 400.

[0022] Among them, the biosensor unit 100 is used to monitor the multimodal data of plant physiological status, rhizosphere microenvironment and meteorological parameters in real time; the neural computing decision engine 200 is used to construct a pulse neural network, integrating the signal conduction mechanism of the plant vascular system and the multi-agent optimization algorithm to generate millisecond-level dynamic irrigation strategies; the driving execution unit 300 is used for millimeter-level water volume regulation and pipe network self-repair of the irrigation execution unit; the communication optimization architecture 400 is used for seamless coverage and secure transmission of irrigation data. At the same time, algorithms such as reinforcement learning are used to optimize the strategy.

[0023] It can be understood that in the embodiments of the present application, the biosensor unit monitors the plant physiology, rhizosphere microenvironment and meteorological parameters in real time in multiple dimensions, the neural computing decision engine integrates the pulse neural network and the bionic algorithm to generate millisecond-level dynamic strategies, and drives the execution unit to achieve millimeter-level precision irrigation and pipe network self-repair. The communication optimization architecture ensures the secure transmission of data and uses reinforcement learning for continuous optimization, thereby improving the utilization rate of water resources, reducing the failure rate of pipe networks, and increasing crop yields, solving the problems of water resource waste and poor irrigation effects in the prior art.

[0024] In the embodiment of the present application, the biosensor unit 100 further includes: Figure 2 As shown, nanoscale plant physiological monitoring and in situ characterization of soil microenvironment.

[0025] Among them, nanoscale plant physiological monitoring is used to detect in real time the ABA concentration in the plant xylem, the organic acid composition in the root system and the turgor pressure status of the stomatal guard cells, providing molecular-level stress warning data; in situ characterization of the soil microenvironment is used to obtain in real time the soil moisture distribution, nutrient status and microbial community abundance, providing in situ data for soil health management and formulating irrigation strategies.

[0026] It can be understood that the embodiments of the present application use nanoscale plant physiological monitoring to detect the ABA concentration in the plant xylem, the organic acid composition of the root system, and the turgor pressure state of the stomatal guard cells in real time, and warn of stress at the molecular level; the in situ characterization of the soil microenvironment obtains the soil moisture distribution, nutrient status, and microbial community abundance in real time, provides in situ data on soil health, and understands the crop growth status and soil conditions.

[0027] For example, in a blueberry plantation, real-time monitoring using the soil microenvironment in situ characterization module revealed that although the surface soil moisture was maintained at 60%, the deep soil moisture was only 35%. At the same time, the abundance of beneficial bacteria in the rhizosphere microbial community decreased by 20% compared with last week. Based on this, it was judged that the root water absorption obstruction may be due to deep drought and reduced microbial activity. Combined with the water requirement for blueberry growth, the irrigation strategy was adjusted to extend the drip irrigation time, reduce the single flow rate, and supplement microbial agents to avoid surface water accumulation and promote root growth to deeper levels. Monitoring two weeks later showed that the deep soil moisture had rebounded to 50%, and the photosynthetic efficiency of blueberry leaves had increased by 15%, ensuring the healthy growth of the plants.

[0028] In the embodiment of the present application, the neural computing decision engine 200 includes: Figure 3 As shown, the spiking neural network building blocks and biologically inspired computing architecture.

[0029] Among them, the pulse neural network construction submodule is used to imitate the pulse emission mechanism of biological neurons, build a pulse neural network model, and process and analyze sensor data; the bio-inspired computing architecture is used to imitate the signal conduction mechanism of the plant vascular system, combining the memristor cross array with the pulse neural network to process biological signals and generate dynamic irrigation strategies.

[0030] For example, in a corn planting base, the bio-inspired computing architecture simulates the conduction mechanism of the plant vascular system and combines memristors with pulse neural networks. When it detects that uneven light leads to different water requirements of corn, the architecture quickly processes data, adjusts the neuron weights through memristors, and regulates the water path in an analogy with the vascular system. It quickly generates precise irrigation strategies, which can increase the photosynthetic efficiency of corn in the affected area by 20% within a week.

[0031] In the embodiment of the present application, the neural computing decision engine 200 further includes: a pulse neural network model, and the formula of the pulse neural network model is: ; in, is the membrane time constant; is the membrane potential; is the resting potential; is the membrane resistance; is the input current; is the time derivative of the membrane potential.

[0032] It can be understood that the embodiments of the present application simulate the biological neuron pulse mechanism through the pulse neural network model, process dynamic data in a time series and event-driven manner, quickly capture subtle changes in the environment, predict and respond in advance, reduce energy consumption through pulse sparse activation, and achieve millisecond-level processing with low power consumption.

[0033] For example, the SNN system based on brain-like hyperdimensional computing is used to collect pulse signal sequences of environmental parameters such as soil moisture, light intensity, temperature and humidity in real time through field sensors. SNN encodes the dynamic changes of data through pulse time interval (ISI). For example, when the soil moisture pulse frequency is lower than the threshold, the system automatically triggers the drip irrigation equipment. At the same time, combined with the pulse characteristics of the plant transpiration rate, the peak water demand is predicted 2 hours in advance, which saves 30% of water compared to traditional PID control and increases the fruit fullness by 25%.

[0034] Specifically, when When , the pulse is triggered and reset, where the deformation formula of the pulse neural network model is: ; ; in, is the membrane potential; is the resting potential; is the membrane time constant; is the membrane capacitance; is the input current; is the issuance threshold; is the change in synaptic weight; is the learning rate; is the time difference between the previous and next neuron pulses; is the time window parameter; is a natural constant.

[0035] In the embodiment of the present application, the neural computing decision engine 200 further includes: a dynamic growth model, the formula of the dynamic growth model is: ; in, is the growth rate; is the inherent growth rate; K is the environmental carrying capacity; is the current population size.

[0036] It can be understood that the embodiments of the present application integrate biological physiological, environmental and genetic data through a dynamic growth model to build a real-time simulation system, accurately depict growth patterns and predict key nodes, reveal growth bottlenecks, provide a quantitative basis for resource allocation, and dynamically adapt to environmental fluctuations.

[0037] In the embodiment of the present application, the driving execution unit 300 includes: Figure 4 As shown, bio-simulation irrigation unit and self-repairing intelligent pipe network.

[0038] Among them, the bio-simulation irrigation unit is used to drive the stomatal structure actuator and magnetically controlled nanoparticle guidance technology to achieve millimeter-level root targeted irrigation; the self-repairing intelligent pipeline network is used to monitor the pipeline network pressure, flow and leakage status in real time, automatically trigger the repair mechanism, and extend the life of the pipeline network.

[0039] It can be understood that the embodiments of the present application use stomatal actuators and magnetically controlled nanotechnology through bio-simulation irrigation units to achieve millimeter-level precision root irrigation, reduce water waste and improve efficiency; the self-repairing intelligent pipe network monitors pressure, flow and leakage in real time, automatically repairs faults and extends life, and reduces maintenance costs.

[0040] For example, the self-repairing pipe network system deployed in the smart farm can sense pipe network abnormalities in real time through built-in pressure sensors and leakage monitoring modules. When micro-cracks are detected in the drip irrigation pipes due to soil settlement, the magnetically controlled nano-repair materials in the pipe network will automatically gather to the damaged area with the water flow, and the magnetic field will trigger the material to expand and seal the leakage point. The repair can be completed without manual inspection, reducing the failure rate of the irrigation system by 60%.

[0041] In the embodiment of the present application, the communication optimization architecture 400 includes: Figure 5 As shown, data transmission interaction engine, network intelligent management and operation and maintenance module, and strategy intelligent optimization feedback unit.

[0042] Among them, the data transmission interaction engine is used to safely and efficiently transmit and interact with multi-source data to support system collaborative operation and decision-making; the network intelligent management and operation and maintenance module is used to build and maintain the communication network topology of the intelligent biological irrigation system in real time, centrally manage network nodes, and use machine learning to diagnose and predict faults to ensure communication stability; the strategy intelligent optimization feedback unit is used to collect irrigation execution data and environmental feedback of the intelligent biological irrigation system, and use reinforcement learning and other algorithms to optimize irrigation strategies and improve irrigation efficiency.

[0043] For example, Figure 6As shown in the figure, the network intelligent management platform integrates full-link monitoring and automated operation and maintenance functions, and conducts real-time status monitoring of 500+ APs, switches and servers in the park. When an abnormal Wi-Fi signal is detected in a certain area, the system automatically analyzes the spectrum interference and remotely adjusts the channel. At the same time, it dispatches drones equipped with signal detectors for on-site verification, which enables network fault handling to be transformed from "manual troubleshooting" to "intelligent self-healing", and the average fault recovery time is shortened from 2 hours to 15 minutes.

[0044] The remote-controlled intelligent biological irrigation system proposed in the embodiment of the present application collects multimodal data of plant physiology, rhizosphere microenvironment and meteorological parameters in real time through the biological sensor unit, laying a solid foundation for precision irrigation; the neural computing decision engine deeply integrates the pulse neural network, the plant vascular system signal transmission mechanism and the multi-agent optimization algorithm, generates dynamic irrigation strategies at the millisecond level, and accurately adapts to the water demand characteristics of crops at different growth stages; the driving execution unit realizes millimeter-level water volume regulation through the stomatal structure actuator, and uses the intelligent pipe network self-repair technology to reduce the risk of failure; the communication optimization architecture not only ensures data security transmission and seamless coverage, but also continuously optimizes the irrigation strategy with the help of reinforcement learning algorithms; it can improve the utilization rate of water resources by more than 40%, reduce soil compaction, adapt to complex farmland environments, and reduce operation and maintenance costs. As a result, the problems of water resource waste, poor irrigation effect, and untimely adjustment of irrigation strategies in the prior art are solved.

[0045] Next, the intelligent biological irrigation method based on remote control proposed in accordance with the embodiment of the present application is described with reference to the accompanying drawings.

[0046] like Figure 7 As shown, the remote control-based intelligent biological irrigation method includes the following steps: In step S101, multimodal data is acquired.

[0047] Among them, multimodal data include plant physiological state, rhizosphere microenvironment and meteorological parameters.

[0048] It can be understood that the embodiments of the present application obtain plant physiology, rhizosphere microenvironment and meteorological parameters to three-dimensionally perceive the crop growth status from the molecular level to the macro environment to avoid irrigation errors.

[0049] For example, nanoprobes implanted in rice stems can be used to detect root organic acid secretion and xylem water transport pressure in real time. Soil sensors buried in different fields can be used to obtain the water content, pH value and abundance of nitrogen-fixing bacteria in the 0-20cm tillage layer. Combined with rainfall, temperature, humidity and other data from field weather stations, a multimodal data set covering plant physiology, soil status and meteorological conditions is formed. Suspend irrigation and start drainage strategies before continuous rainy days to avoid root hypoxia and root rot. At the same time, accurately add fertilizers according to changes in soil microbial activity after rain to improve rice tillering rate and disease resistance.

[0050] In step S102, a spiking neural network is constructed based on the multimodal data, and a dynamic irrigation strategy is generated based on the spiking neural network fusion signal conduction mechanism and optimization algorithm.

[0051] Among them, the signal transduction mechanism refers to the process in which extracellular signals bind to receptors on the cell membrane, triggering a cascade reaction of a series of signal transduction pathways within the cell, transmitting the signal to specific targets within the cell, thereby regulating the physiological functions and behaviors of the cell.

[0052] It can be understood that the embodiments of the present application use signal transduction mechanisms to simulate the entire process of plants from sensing environmental stimuli to initiating physiological responses, thereby helping the irrigation system to accurately capture the real needs of crops, dynamically optimize water supply strategies, improve water use efficiency and crop resistance, and reduce human experience decision-making bias.

[0053] For example, the intelligent irrigation system simulates the signal conduction mechanism of cotton plants. When the nanosensor detects that the ABA concentration in the leaves increases due to high temperature and water shortage, the "water shortage signal" is quickly transmitted to the decision-making platform through the pulse neural network, analogous to the signal conduction pathway of the cotton xylem. The platform then combines soil moisture data and imitates the plant vascular system's strategy of prioritizing water supply to the reproductive organs based on the bio-inspired computing architecture. It dynamically adjusts the irrigation plan by reducing the amount of water during the period of active leaf transpiration, and instead uses stomatal actuators to accurately deliver water to the key areas of cotton boll development, effectively preventing buds and bolls from falling off, increasing the cotton boll rate by 20%, and saving 35% water.

[0054] In step S103, according to the dynamic irrigation strategy, millimeter-level water volume regulation and irrigation are performed, the leakage point of the pipe network is automatically located and the backup pipeline is started.

[0055] Among them, the dynamic irrigation strategy refers to a precise irrigation plan that can be adjusted in real time with environmental changes and crop growth processes, generated by integrating multi-agent optimization algorithms with pulse neural networks and bio-inspired computing architectures.

[0056] It can be understood that the embodiments of the present application integrate multi-source data of plant physiology, soil microenvironment and meteorology in real time, and use intelligent algorithms to dynamically adjust irrigation time, water volume and path, accurately match changes in crop water requirements, reduce water resource waste, increase crop yields, and at the same time reduce soil compaction and nutrient loss.

[0057] For example, the irrigation strategy is adjusted dynamically through pulse neural networks and multi-agent algorithms. In the three weeks before flowering, the irrigation frequency is increased from 2 times a day to 3 times a day, and the single water volume is reduced based on the changes in plant hormones and the nitrogen conversion efficiency of soil microorganisms. In the event of sudden heavy rains, irrigation is automatically suspended and the drainage program is started. At the same time, precise supplementary irrigation is carried out to maintain moisture content based on the soil moisture recovery curve after rain.

[0058] In step S104, the data such as soil moisture and irrigation amount after irrigation are securely transmitted to the decision-making platform for data coverage. At the same time, the strategy is adjusted and optimized according to the actual irrigation effect.

[0059] Among them, the decision-making platform is the core center that automatically generates and dynamically adjusts irrigation strategies based on the multimodal data of the intelligent biological irrigation system, using pulse neural networks, bio-inspired computing architecture and optimization algorithms.

[0060] It can be understood that the embodiments of the present application integrate plant physiology, soil microenvironment and meteorological multimodal data, and use pulse neural networks and bio-inspired algorithms to intelligently generate dynamic irrigation strategies, thereby achieving precise on-demand irrigation, improving water resource utilization efficiency, reducing operation and maintenance costs, and promoting healthy growth of crops.

[0061] For example, the decision-making platform uses pulse neural networks, bio-inspired computing architectures and multi-agent optimization algorithms to conduct in-depth analysis, accurately determine the growth status and water requirements of tomatoes, and dynamically adjust irrigation time, water volume and frequency; in hot and rainy weather, it promptly increases irrigation volume and adjusts irrigation periods to morning and evening to ensure that tomatoes have adequate water supply and that the fruits are plump and juicy. Compared with traditional irrigation methods, tomato yields have increased by 25%.

[0062] According to the remote-controlled intelligent biological irrigation method proposed in the embodiment of the present application, the multimodal data of plant physiology, rhizosphere microenvironment and meteorological parameters are collected in real time through the biological sensor unit, laying a solid foundation for precision irrigation; the neural computing decision engine deeply integrates the pulse neural network, the plant vascular system signal transmission mechanism and the multi-agent optimization algorithm, generates dynamic irrigation strategies at the millisecond level, and accurately adapts to the water demand characteristics of crops at different growth stages; the driving execution unit realizes millimeter-level water volume regulation through the stomatal structure actuator, and uses the intelligent pipe network self-repair technology to reduce the risk of failure; the communication optimization architecture not only ensures data security transmission and seamless coverage, but also continuously optimizes the irrigation strategy with the help of reinforcement learning algorithms; it can increase the utilization rate of water resources by more than 40%, reduce soil compaction, adapt to complex farmland environments, and reduce operation and maintenance costs. As a result, the problems of water resource waste, poor irrigation effect, and untimely adjustment of irrigation strategies in the prior art are solved.

[0063] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include: A memory 801 , a processor 802 , and a computer program stored in the memory 801 and executable on the processor 802 .

[0064] When the processor 802 executes the program, the intelligent biological irrigation system based on remote control provided in the above embodiment is implemented.

[0065] Furthermore, the electronic device further comprises: The communication interface 803 is used for communication between the memory 801 and the processor 802 .

[0066] The memory 801 is used to store computer programs that can be executed on the processor 802 .

[0067] The memory 801 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0068] If the memory 801, the processor 802 and the communication interface 803 are implemented independently, the communication interface 803, the memory 801 and the processor 802 can be connected to each other through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0069] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can communicate with each other through an internal interface.

[0070] The processor 802 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0071] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms is not necessarily for the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0072] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0073] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0074] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0075] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. Intelligent biological irrigation system based on remote control, characterized in that: include: Biosensor unit, neural computing decision engine, drive execution unit, communication optimization architecture; among them, The biosensor unit is used to monitor multimodal data of plant physiological status, rhizosphere microenvironment and meteorological parameters in real time; The neural computing decision engine is used to construct a pulse neural network, integrate the plant vascular system signal transmission mechanism and the multi-agent optimization algorithm, and generate a millisecond-level dynamic irrigation strategy; The driving execution unit is used for millimeter-level water volume regulation and pipe network self-repair of the irrigation execution unit; The communication optimization architecture is used for seamless coverage and secure transmission of irrigation data. At the same time, algorithms such as reinforcement learning are used to optimize the strategy.

2. The remote-controlled intelligent biological irrigation system according to claim 1, characterized in that: The biosensor unit includes nanoscale plant physiological monitoring and in-situ characterization of the soil microenvironment. The nanoscale plant physiological monitoring is used to detect the ABA concentration in the plant xylem, the organic acid composition in the root system and the turgor pressure state of the stomatal guard cells in real time, and provide stress warning data at the molecular level; the in-situ characterization of the soil microenvironment is used to obtain soil moisture distribution, nutrient status and microbial community abundance in real time, provide in-situ data for soil health management, and formulate irrigation strategies.

3. The remote-controlled intelligent biological irrigation system according to claim 1, characterized in that: The neural computing decision engine includes a pulse neural network construction submodule and a bio-inspired computing architecture, wherein the pulse neural network construction submodule is used to imitate the pulse emission mechanism of biological neurons, construct a pulse neural network model, and process and analyze sensor data; the bio-inspired computing architecture is used to imitate the signal conduction mechanism of the plant vascular system, combine the memristor cross array with the pulse neural network, process biological signals, and generate dynamic irrigation strategies.

4. The remote-controlled intelligent biological irrigation system according to claim 3 is characterized in that: The neural computing decision engine includes a dynamic growth model, which is used to integrate satellite remote sensing and ground sensor data, combine a multi-agent system, and coordinate optimization algorithms to predict the spatiotemporal distribution of crop water requirements.

5. The remote-controlled intelligent biological irrigation system according to claim 3 is characterized in that: The neural computing decision engine also includes a pulse neural network model, and the formula of the pulse neural network model is: ； in, is the membrane time constant; is the membrane potential; is the resting potential; is the membrane resistance; is the input current; is the time derivative of the membrane potential.

6. The remote-controlled intelligent biological irrigation system according to claim 4, characterized in that: The neural computing decision engine also includes a dynamic growth model, and the formula of the dynamic growth model is: ； in, is the growth rate; is the inherent growth rate; K is the environmental carrying capacity; is the current population size.

7. The remote-controlled intelligent biological irrigation system according to claim 1, characterized in that: The driving execution unit includes a biosimulation irrigation unit and a self-repairing intelligent pipe network, wherein the biosimulation irrigation unit is used to drive the stomatal structure actuator and the magnetically controlled nanoparticle guidance technology to achieve millimeter-level root targeted irrigation; the self-repairing intelligent pipe network is used to monitor the pipe network pressure, flow and leakage status in real time, automatically trigger the repair mechanism, and extend the life of the pipe network.

8. The remote-controlled intelligent biological irrigation system according to claim 1, characterized in that: The communication optimization architecture includes a data transmission interaction engine, a network intelligent management and operation and maintenance module, and a strategy intelligent optimization feedback unit. The data transmission interaction engine is used to safely and efficiently transmit and interact with multi-source data to support system collaborative operation and decision-making; the network intelligent management and operation and maintenance module is used to build and maintain the communication network topology of the intelligent biological irrigation system in real time, centrally manage network nodes, use machine learning to diagnose and predict faults, and ensure communication stability; the strategy intelligent optimization feedback unit is used to collect irrigation execution data and environmental feedback of the intelligent biological irrigation system, and use algorithms such as reinforcement learning to optimize irrigation strategies and improve irrigation efficiency.

9. A method for applying to a remote-controlled intelligent biological irrigation system according to any one of claims 1 to 8, characterized in that: The method comprises: Acquiring multimodal data, wherein the multimodal data includes plant physiological state, rhizosphere microenvironment and meteorological parameters; Constructing a spiking neural network according to the multimodal data, and generating a dynamic irrigation strategy based on the spiking neural network fusion signal conduction mechanism and optimization algorithm; According to the dynamic irrigation strategy, millimeter-level water volume regulation and irrigation are carried out, and the leakage point of the pipe network is automatically located and the backup pipeline is started; The soil moisture, irrigation amount and other data after the irrigation are securely transmitted to the decision-making platform for data coverage. At the same time, the strategy is adjusted and optimized according to the actual irrigation effect.

10. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the remote-controlled intelligent biological irrigation system according to any one of claims 1 to 8.

Images