Nursery stock fixation stability intelligent detection and reinforcement decision-making system

Abstract

The invention discloses a nursery stock fixing stability intelligent detection and reinforcement decision-making system, and relates to the field of nursery stock fixing and monitoring. The multi-source data acquisition module is provided with a bionic sensor and transmits data by adopting quantum encryption; the data preprocessing module separates physiological and mechanical signals through wavelet packet decomposition and Kalman filtering; the stability evaluation module synthesizes the seedling parameters and the root system fixation force based on an ecological mechanical model; the intelligent decision-making module fuses genetic and ant colony algorithms to generate a multi-objective optimization scheme; and the execution control module adopts a shape memory polymer supporting system and a magnetorheological elastomer device to realize self-adaptive adjustment and self-repairing. The nursery stock stability is accurately monitored in real time, the reinforcement scheme cost is reduced, and the nursery stock survival rate is increased; the self-adaptive adjusting and self-repairing capabilities are realized, and the energy self-sufficiency rate is high; degradable materials are adopted, the ecological environmental protection requirement is met, and the nursery stock management efficiency and the intelligent level are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of seedling fixation and monitoring technology, and in particular to an intelligent detection and reinforcement decision system for seedling fixation stability. Background Technology

[0002] In urban greening, ecological restoration, and forestry projects, the fixation and stability of transplanted seedlings are crucial to their survival rate and growth quality. Traditional seedling fixation methods rely heavily on manual experience, using simple support structures such as wooden stakes, ropes, or metal frames, and reinforcing the seedlings by visually assessing their tilt. This method has significant drawbacks: the selection of support points and angles lacks scientific basis and is difficult to adapt to differences in seedling varieties, sizes, and growing environments; furthermore, the fixing devices are mostly for single use and cannot be adjusted according to the dynamic growth of the seedlings, leading to premature support failure or marks on the seedling stems, affecting their normal growth. Seedlings fixed using traditional methods have a high lodging rate when encountering extreme weather such as strong winds and heavy rains, significantly increasing subsequent maintenance costs and replanting pressure.

[0003] Existing methods for assessing seedling stability also have significant shortcomings. Some studies rely on regular manual inspections to measure indicators such as seedling tilt angle and swaying, but manual inspection is inefficient, subjective, and lacks real-time monitoring and early warning capabilities. While some intelligent monitoring systems incorporate sensor technology, they are often limited to single-parameter detection (e.g., monitoring only tilt angle), lacking comprehensive analysis of multi-dimensional data such as internal stress, root adhesion, and environmental meteorological factors, making it difficult to accurately assess the actual stability of seedlings. Furthermore, existing detection and reinforcement systems operate independently, failing to achieve data-driven intelligent decision-making. This results in reinforcement measures lagging behind the occurrence of risks, thus failing to effectively ensure seedling safety.

[0004] With the increasing demands for smart city construction and ecological protection, traditional seedling fixation and monitoring technologies are no longer sufficient to meet the needs of modern landscape management and forestry engineering. On the one hand, urban greening places increasingly stringent requirements on seedling survival rates, landscape effects, and ecological benefits, necessitating precise and efficient stability assurance solutions. On the other hand, large-scale ecological restoration projects involve a massive number of seedlings, making traditional manual management methods costly and inefficient. Therefore, developing a seedling fixation stability detection system that integrates multi-source data acquisition, intelligent assessment, and dynamic reinforcement has become an urgent need to address current industry pain points and promote the intelligent development of forestry. Summary of the Invention

[0005] The present invention proposes an intelligent detection and reinforcement decision system for seedling fixation stability to solve the problems mentioned in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: an intelligent detection and reinforcement decision-making system for seedling fixation stability, comprising:

[0007] Multi-source data acquisition module: Deploys a biomimetic distributed sensor network and uses quantum encryption technology to transmit data; it uses a self-organizing network via the ZigBee protocol, with a data transmission frequency of 10Hz and a key update frequency of once per hour;

[0008] Data preprocessing module: Develops a feature extraction algorithm for seedling physiological signals, separates mechanical vibration and physiological activity signals through wavelet packet decomposition, and fuses sensor data using Kalman filtering to construct a seedling stress-growth coupling model M = α·S. mech +β·S physio +γ·F Kalman M is the output of the coupled model, α and β are the signal weighting coefficients, and S mech Mechanical vibration signal, S physio Physiological activity signal, gamma filter coefficient, F Kalman Kalman filter output; sliding window algorithm is used to smooth time series data and eliminate measurement noise;

[0009] Stability assessment module: Constructs an ecomechanical assessment model for seedlings, integrating fluid dynamics effects, material nonlinearity, and root fixation field; introduces the stress relaxation coefficient of seedling growth, establishes a time-varying stability assessment model, and sets a safety threshold;

[0010] Intelligent Decision Module: Constructs a seedling-environment-consolidation co-evolutionary algorithm, integrating genetic algorithm and ant colony algorithm, adopting a multi-objective optimization algorithm, and introducing the co-evolutionary fitness formula F=ω1·f1(x). －1 +ω2·f2(x), where F is the synergistic fit, f1 is the reinforcement cost function, f2 is the expected stable improvement function, ω1 and ω2 are weight coefficients and ω1+ω2=1; the optimal solution is determined by the Pareto optimal solution, and a multi-stage reinforcement strategy is dynamically generated and seasonally adaptively adjusted;

[0011] Execution control module: Design a shape memory polymer-based intelligent support system, develop photothermal response, self-healing, and biodegradation functions; adopt a magnetorheological elastomer intelligent support device to automatically adjust the support angle and tension.

[0012] Furthermore, it also includes:

[0013] Early warning response module: When the monitoring data triggers the three-level early warning mechanism, the system automatically sends SMS and email notifications, activates emergency support devices, and triggers the emergency response program of the ecological monitoring module.

[0014] Furthermore, it also includes:

[0015] Digital Twin Optimization Module: Establish a three-dimensional mechanical digital twin model of seedlings, solve the dynamic mechanical equations using the meshless Galerkin method, develop a real-time data synchronization protocol, and bidirectionally map the physical entity and the virtual model; optimize the parameters of the digital twin model based on reinforcement learning, and automatically execute the optimized reinforcement scheme through smart contracts.

[0016] Furthermore, the stability assessment module introduces a root fixation correction coefficient to correct the stability coefficient calculation under different soil conditions; and uses viscoelastic mechanics theory combined with the stress relaxation effect during seedling growth to predict the evolution of seedling stability.

[0017] Furthermore, the intelligent decision-making module constructs a multi-objective game decision-making algorithm that integrates economic costs, ecological impacts, and social benefits, and solves for the optimal strategy combination through Nash equilibrium.

[0018] Furthermore, it also includes:

[0019] Energy self-sustaining module: Develop blade-type triboelectric nanogenerator and seedling transpiration energy harvesting device, and use supercapacitor bank to store energy; combine dynamic power management algorithm to dynamically adjust system power consumption according to sensor sampling frequency.

[0020] Furthermore, the multi-source data acquisition module deploys a UAV mobile monitoring node, equipped with lidar and a hyperspectral imager, based on A... * The algorithm autonomously plans routes; sensor fusion positioning technology is used to inspect the seedling community and collect data.

[0021] Furthermore, it also includes:

[0022] Bio-mechanical synergistic reinforcement module: Design plant-induced growth scaffolds and regulate plant phototropism through blue LEDs; develop a microbial soil improvement system and inoculate rhizobia and phosphate-solubilizing bacteria; construct a root-support structure mechanical synergistic model to couple and enhance the effects of biological reinforcement and artificial reinforcement.

[0023] Furthermore, the execution control module adopts a magnetorheological elastomer intelligent support device, with a built-in piezoelectric sensor array for self-diagnosis of faults, and a photocatalytic coating on its surface.

[0024] Furthermore, it also includes:

[0025] Blockchain Trust Management Module: Establish a seedling lifecycle management alliance chain, design a smart contract automatic execution reinforcement scheme, and store seedling stability data; adopt zero-knowledge proof technology to protect data privacy.

[0026] Compared with existing technologies, the beneficial effects of this invention are:

[0027] Through the integration of multiple technologies and innovative design, the level of intelligence and practical application effect of seedling management are comprehensively improved. At the detection level, a biomimetic distributed sensor network and multi-source data fusion technology are adopted to achieve real-time and accurate monitoring of seedling internal stress, crack propagation, physiological state and environmental parameters. Compared with traditional single-point detection, the accuracy is improved, and potential risks can be identified in advance to avoid seedling lodging caused by human inspection oversight.

[0028] The intelligent decision-making module automatically generates the optimal reinforcement strategy by constructing an ecomechanical assessment model and a co-evolutionary algorithm, comprehensively considering the characteristics of the seedlings themselves, environmental factors, and reinforcement costs. It dynamically adjusts the support scheme according to seasonal changes and meteorological conditions; for example, it proactively strengthens the support before typhoons and intelligently adjusts the support angle during the peak growing season, ensuring stability while minimizing the impact on seedling growth. Compared to traditional fixing methods, this improves seedling survival rates and reduces maintenance costs.

[0029] The execution control module utilizes smart materials such as shape memory polymers and magnetorheological elastomers, enabling the support device to possess adaptive adjustment, self-healing, and biodegradable characteristics. The support device can automatically adjust its stiffness and damping according to the actual stress on the seedlings, effectively buffering external impacts; the microcapsule repair agent can autonomously repair material cracks, extending the device's service life; the application of biodegradable materials avoids the problems of difficult dismantling and environmental pollution associated with traditional support devices, meeting ecological and environmental protection requirements.

[0030] In addition, the system integrates functions such as energy self-sufficiency and blockchain management. Through triboelectric nano-power generation and transpiration energy harvesting technology, it achieves energy self-sufficiency. Blockchain technology ensures credible data storage and accountability, providing a full-process digital solution for garden management and promoting the development of seedling fixing and monitoring technology towards intelligence, ecology, and sustainability. Attached Figure Description

[0031] Figure 1 This is a schematic block diagram of an intelligent detection and reinforcement decision system for seedling fixation stability proposed in this invention;

[0032] Figure 2 A diagram comparing the accuracy of seedling stability detection using different sensor layout schemes;

[0033] Figure 3 A diagram comparing the costs and effectiveness of different reinforcement solutions;

[0034] Figure 4 A diagram showing the comparison of energy self-sufficiency rates under different weather conditions;

[0035] Figure 5 A diagram showing the comparison of prediction errors in seedling stability assessment models;

[0036] Figure 6This is a diagram showing the comparison of seedling survival rates when the system triggers a three-level early warning. Detailed Implementation

[0037] 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.

[0038] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0039] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. The invention will now be described in further detail with reference to the accompanying drawings.

[0040] Reference Figures 1 to 6 A smart detection and reinforcement decision-making system for seedling fixation stability, comprising:

[0041] Multi-source data acquisition module: In the seedling planting area, sensors are deployed according to the size and distribution of the seedlings, mimicking the radial distribution of plant roots based on biomimetic principles. Each seedling is equipped with three micro-strain fiber sensors, which are implanted into the phloem of the seedling using minimally invasive implantation technology. The sensors are encapsulated in polyimide, with a diameter of only 0.3 mm, and the implantation depth is 1 / 3 of the seedling stem radius to minimize the impact on seedling growth. The built-in MEMS strain gauges can achieve 10...－6 High-resolution strain monitoring was implemented. Simultaneously, one acoustic emission sensor was installed at the root and another at the middle of the seedling. The sensor frequency response range was set to 20-100kHz, and they were tightly bonded to the seedling surface using a special coupling agent to capture elastic wave signals generated during the propagation of internal cracks. A spectral imager was installed 1m above the seedling canopy, employing a push-broom imaging method with a wavelength range covering 400-750nm and a spectral resolution of 3nm, capable of acquiring chlorophyll fluorescence spectrum data of the seedling leaves. In addition, a triaxial accelerometer (range ±16g), a laser rangefinder (error <0.5°), a soil moisture sensor (range 0-100%), and a miniature weather station (wind speed measurement accuracy ±0.3m / s, wind direction ±3°, rainfall ±0.2mm / h) were deployed. All sensors are equipped with low-power ZigBee communication modules, forming a self-organizing network with a data transmission frequency set to 10Hz. To ensure data security, quantum key distribution technology is used to generate symmetric keys, with a key update frequency of once per hour. Data transmission is encrypted using the AES-256 encryption algorithm. Simultaneously, mobile monitoring nodes are deployed using drones equipped with lidar (scanning point cloud density of 100 points / m²). 2 ) and a hyperspectral imager (224 bands), based on A * The algorithm plans the inspection path and performs a rapid scan of the entire planting area every 2 hours to supplement data collection on a large scale of seedling communities.

[0042] Data preprocessing module: Collected multi-source data is transmitted to edge computing nodes for preliminary processing. For nonlinear signals acquired by micro-strain fiber sensors and acoustic emission sensors, an 8-level wavelet packet decomposition using the db4 wavelet basis is performed to decompose the signal into different frequency bands. Noise signals are removed by setting an adaptive threshold. The Kalman filter algorithm is used to fuse multi-sensor data and establish a state-space model. Parameters such as the seedling's tilt angle, vibration frequency, and internal stress are used as state variables to achieve accurate estimation of the seedling's actual state. A seedling stress-growth coupling model M = α·S is constructed. mech +β·S physio +γ·F Kalman M is the output of the coupled model, α and β are the signal weighting coefficients, and S mech Mechanical vibration signal, S physio Physiological activity signal, gamma filter coefficient, F KalmanKalman filter output. For time-series data, a sliding window algorithm (window size set to 50 data points, sliding step size of 5) is used for smoothing to eliminate data fluctuations. A specialized algorithm for extracting physiological signal features of seedlings is developed. By analyzing chlorophyll fluorescence spectrum data, physiological indicators such as photosynthetic efficiency and photosystem II activity of seedlings are extracted and separated from mechanical vibration signals. A seedling stress-growth coupling model is constructed to identify the impact of environmental disturbances on seedling stability, effectively improving data quality and usability.

[0043] Stability Assessment Module: Based on an improved analytic hierarchy process (AHP) combined with a seedling ecomechanical assessment model, this module evaluates seedling stability. The model comprehensively considers parameters such as seedling height H (m), diameter at breast height (DBH) D (cm), crown width W (m), and support angle θ (°), calculating a comprehensive stability coefficient K = α·H. －1 The stability is quantified by the formula: +β·D+γ·cosθ (where α=0.3, β=0.4, γ=0.3). A root fixation correction coefficient η=1+0.2·e is introduced. (-0.1ρ) (ρ represents soil compaction, in kg / m³) 3 Soil compaction is calculated based on data collected by soil moisture sensors and miniature pressure sensors, and the overall stability coefficient is corrected accordingly. Considering the stress relaxation effect during seedling growth, and combining viscoelastic mechanics theory, a seedling growth stress relaxation coefficient λ = e is introduced. (-t / τ) (t represents time, and τ represents the material relaxation time constant) A time-varying stability assessment model is established. By periodically measuring the growth parameters of the seedlings (such as stem diameter growth and root expansion), the model parameters are updated to predict the evolution trend of seedling stability over time. A safety threshold K ≥ 0.8 is set; when the K value falls below this threshold, a corresponding early warning mechanism is triggered.

[0044] Intelligent Decision-Making Module: Employs a seedling-environment-reinforcement co-evolutionary algorithm, integrating the advantages of genetic algorithms and ant colony algorithms. Based on a historical case database (containing over 5000 seedling reinforcement cases) and real-time monitoring data, it determines decision variables such as support material type (wood, metal, composite material), support point location (height h = 0.6H above ground), and reinforcement angle (45-60° with ground). In the genetic algorithm, the population size is set to 100, crossover probability 0.8, and mutation probability 0.05, continuously evolving the population through selection, crossover, and mutation. In the ant colony algorithm, the pheromone volatility coefficient is set to 0.3, and ants select paths based on pheromone concentration and heuristic information during the search process. A multi-objective optimization algorithm is employed, introducing the co-evolutionary fitness formula F = ω1·f1(x). －1+ω2·f2(x), where F is the co-fit degree, f1 is the reinforcement cost function, f2 is the expected stable improvement function, and ω1 and ω2 are weight coefficients with ω1+ω2=1. The optimal solution is determined through Pareto optimality, achieving a balance between economic benefits and reinforcement effectiveness. The system supports seasonal adaptive adjustment, automatically adjusting decision-making strategies based on seasonal variation data (such as wind speed, rainfall, and temperature) monitored by micro-weather stations. For example, before the typhoon season, the support strength is strengthened in advance by selecting more robust metal support materials; during the peak growth season of seedlings, the support point positions are appropriately adjusted to avoid affecting the normal growth of seedlings.

[0045] The execution control module employs a shape memory polymer-based intelligent support system and a magnetorheological elastomer intelligent support device. The shape memory polymer support component uses polylactic-co-glycolic acid copolymer (PLGA) as the matrix, reinforced with carbon nanotubes, and is given its initial shape through thermoforming during manufacturing. When the ambient light intensity is ≥8000 lux, the support component absorbs light energy and converts it into heat energy, triggering the shape memory effect and automatically adjusting the support angle and tension with a response time <2s. The component is internally encapsulated with microcapsule repair agents (mainly epoxy resin and curing agent). When a crack is detected in the material, the microcapsules rupture and release the repair agent, achieving self-repair with a repair efficiency ≥90%, and the material is completely biodegradable within 3-5 years. The magnetorheological elastomer intelligent support device is prepared using a composite of iron powder and silicone rubber. By changing the external magnetic field strength (0-1T), the modulus can be adjusted within the range of 0.5-10MPa, and the damping ratio can be dynamically adjusted between 0.1-0.6. The device incorporates a stepper motor (positioning accuracy ±0.1°, maximum output torque 50 N·m) and a piezoelectric sensor array. The piezoelectric sensors monitor the stress and operating status of the support device in real time. When an anomaly is detected, the system automatically diagnoses the fault and adjusts the control strategy accordingly. The surface of the support device is coated with a titanium dioxide photocatalytic coating, which can degrade organic pollutants in the surrounding environment under light conditions with a degradation efficiency of ≥85%, thus also serving an environmental purification function.

[0046] This invention also includes the following modules:

[0047] Early Warning Response Module: The system employs a three-tiered early warning mechanism: Yellow Alert (K∈[0.6,0.8)), Orange Alert (K∈[0.4,0.6)), and Red Alert (K<0.4). When a Yellow Alert is triggered, the system notifies administrators via SMS and email, and displays the location and detailed information of the alerted seedlings on the management platform. For an Orange Alert, in addition to notification, auxiliary support devices, such as deployable hydraulic supports, are automatically activated. The initial support force is adjusted to 100N and dynamically adjusted according to actual conditions. For a Red Alert, an emergency reinforcement procedure is immediately initiated, and an alarm is sent to relevant departments to implement emergency protection measures. The Early Warning Response Module is linked with the Ecological Monitoring Module. When an alert is triggered, the Ecological Monitoring Module increases the monitoring frequency, using a miniature insect radar (50m monitoring range, 0.5m resolution) and a soil microbial sensor (based on 16S rRNA gene sequencing technology) to monitor changes in the biological community and soil microorganisms around the seedlings in real time, assessing the ecological impact and providing data support for subsequent ecological restoration and management.

[0048] This invention also includes the following modules:

[0049] Digital Twin Optimization Module: This module utilizes binocular vision sensors to collect 3D point cloud data of seedlings, maintaining a distance of 2-3 meters between the sensors and the seedlings during acquisition, and covering the entire circumference of the seedlings. Point cloud registration is achieved through the Iterative Closest Point (ICP) algorithm, constructing a high-precision digital twin model of the seedlings with a spatial resolution of 5mm. A dedicated data synchronization protocol is developed, employing UDP communication to achieve bidirectional real-time mapping between the physical entity and the virtual model, with a data latency of <10ms. The digital twin model is optimized based on reinforcement learning (PPO algorithm), with a reward function set to reward or penalize based on the error between the model's prediction results and the actual monitoring data. During training, the learning rate is set to 0.0003, the batch size to 64, and the number of iterations to 1000. Model parameters are continuously adjusted to gradually improve the prediction accuracy to 97.8%. The optimized model can simulate the mechanical response of seedlings under different wind conditions (wind speed range 0-30m / s) in real time, providing more accurate prediction data for the intelligent decision-making module. Simultaneously, the optimized reinforcement scheme is automatically executed through smart contracts, improving decision-making efficiency and accuracy.

[0050] In this invention, the stability assessment module introduces a correction coefficient based on soil compaction by constructing a quantitative model of soil-root interaction. Soil compaction reflects the tightness of particle arrangement, affecting root penetration resistance and anchoring force. This correction coefficient, calibrated through indoor pull-out tests and in-situ field tests, can correct traditional stability coefficient calculations based on soil compaction data for different forest types and soil depths. For example, in clay soils, high compaction weakens root hold-up, making the assessment results more consistent with actual mechanical scenarios. Combining viscoelastic mechanics theory, a dynamic assessment model is built based on seedling structural characteristics. The seedling is simplified as a parallel system of elastic and viscous elements, simulating instantaneous elastic deformation and stress relaxation time effects. By long-term monitoring of seedling growth data (plant height, diameter at breast height curves) and wind-induced vibration response, the correlation between growth parameters and viscoelastic parameters is established. In the early stages of growth, the xylem is not fully developed, resulting in significant stress relaxation; as growth progresses, elasticity increases, and the relaxation rate decreases. This coupled model can predict the evolution trend of stability over time, make up for the shortcomings of traditional static assessment, provide dynamic assessment basis for risk warning during the seedling cultivation cycle, and improve the accuracy of long-term assessment.

[0051] In this invention, the intelligent decision-making module proposes a multi-objective game theory decision-making algorithm to balance economic, ecological, and social benefits. The economic cost objective is controlled by quantifying expenditures throughout the entire process and flexibly adjusting the proportion of investment in different plans. The ecological impact objective employs a spatiotemporal two-dimensional analysis model, combined with GIS data to dynamically simulate the disturbance and diffusion of soil, vegetation, and other elements. The social benefit objective considers dimensions such as livelihood security, determines weights using the Delphi method, and quantifies social utility indicators using big data. The algorithm abstracts the three main objective subjects as game participants: the economic subject pursues cost minimization, the ecological subject constrains environmental impact, and the social subject strives for benefit maximization. By constructing a multi-objective optimization model, Pareto optimality theory is used to generate a solution set, and an improved genetic algorithm is used to search for Pareto front solutions under constraints. The fitness function integrates the three objectives, and iterative optimization is performed through selection, crossover, and mutation operations. The constraint handling mechanism ensures that hard indicators such as ecological red lines are not breached. Based on project priorities, the optimal strategy combination is determined from the frontier solutions, achieving a multi-dimensional balance of reasonable economic input, controllable ecological disturbance, and improved social benefits, providing quantitative decision-making support for efficient resource allocation.

[0052] This invention also includes the following modules:

[0053] The self-sustaining energy module consists of a blade-type triboelectric nanogenerator, a seedling transpiration energy harvesting device, and a supercapacitor bank. The blade-type triboelectric nanogenerator, using polytetrafluoroethylene (PTFE) and copper electrode materials, is designed in a biomimetic blade shape and installed on the outer periphery of the seedling canopy. When the blades sway in the wind, they generate electricity through triboelectric charging, achieving an output power density of up to 3.2 W / m². 2The seedling transpiration energy harvesting device utilizes the humidity difference generated by seedling transpiration to convert heat energy into electrical energy through a thermoelectric conversion material (Bi2Te3-based alloy), achieving an energy conversion efficiency of 18.5%. The supercapacitor bank uses activated carbon electrode material with a specific energy of 45Wh / kg, and an energy management system stores and distributes the electrical energy. The system dynamically adjusts power consumption based on sensor sampling frequency and the operating status of each module; for example, it reduces data acquisition frequency and the operating power of some modules at night or when the seedlings are in a stable state. Testing showed that the system can operate normally for 32 days using stored electrical energy during continuous rainy weather, effectively ensuring continuous operation and reducing dependence on external power sources.

[0054] In this invention, a multi-source data acquisition module is deployed using a mobile monitoring node on a drone to construct an efficient data acquisition system for seedling communities. The drone carries a point cloud density of 100 points / m². 2 The lidar, utilizing high-frequency laser pulse reflection signals, accurately captures the three-dimensional structure of seedling communities (such as tree height and crown width); equipped with a hyperspectral imager with ≥200 bands, covering the visible-near-infrared spectrum, it identifies species and monitors physiological states (chlorophyll, water, etc.) using the spectral reflectance characteristics of seedlings. Path planning is based on A * The algorithm first rasterizes the monitoring area and sets start and end points. It then uses an evaluation function to search for the optimal path and dynamically adjusts it based on community geographic information (terrain, obstacles) to ensure efficient coverage and obstacle avoidance in complex environments, achieving intelligent inspection path planning. Positioning is achieved by fusing GPS and visual SLAM. GPS provides global latitude, longitude, and altitude information; visual SLAM uses camera images and feature point matching to construct a map and calculate pose. The two are fused using Kalman filtering. When the GPS signal is strong, it corrects visual SLAM errors; when the signal is weak, visual SLAM ensures continuous positioning, achieving a positioning accuracy of ±0.3m. This supports stable drone flight and accurate data collection, laying a solid foundation for seedling community ecological analysis and growth monitoring.

[0055] This invention also includes the following modules:

[0056] Bio-mechanical synergistic reinforcement module: A plant-induced growth scaffold is designed with an adjustable structure and a surface-mounted blue LED light (wavelength 450nm). The light intensity can be adjusted within the range of 100-1000 lux according to the seedling growth requirements. By regulating plant phototropism, the seedling stems are guided to grow in a predetermined direction, promoting natural reinforcement. Simultaneously, a microbial soil improvement system is developed, inoculating the soil around the seedling roots with rhizobia (nitrogen fixation efficiency ≥25 kg / ha·year) and phosphate-solubilizing bacteria to improve soil fertility and the root growth environment. A root-support structure mechanical synergistic model is constructed, using sensors to monitor the forces exerted by root growth on the soil and the supporting force of the support device on the seedlings. The mechanical relationship between the two is analyzed to achieve a synergistic effect of biological and artificial reinforcement. For example, when increased soil compaction is detected due to root growth, the supporting force of the support device can be appropriately reduced to fully utilize the seedling's inherent stability, reduce human intervention, and achieve eco-friendly seedling fixation and management.

[0057] In this invention, the execution control module employs a magnetorheological elastomer intelligent support device. Using a polymer matrix containing magnetic particles as the matrix, a controllable magnetic field is generated by passing currents of varying intensities through a precise magnetic field generating unit. This reconstructs the microstructure of the internal magnetic particles, achieving adjustable magnetic field response stiffness from 0.5-10 MPa to adapt to different working conditions. Adaptive damping control, based on vibration parameters collected by built-in sensors, adjusts the damping characteristics according to an algorithm, dynamically adjusting the damping ratio from 0.1-0.6 to handle complex vibrations. A built-in piezoelectric sensor array utilizes the positive piezoelectric effect to convert the mechanical signals of the support device's deformation under stress into electrical signals. After processing and comparison, fault self-diagnosis is achieved. A photocatalytic coating, with titanium dioxide as the core, produces active substances under light, achieving an organic pollutant degradation efficiency >85%. Attached using a special coating process, it combines mechanical properties with environmentally friendly attributes, contributing to system performance optimization and environmental friendliness. Simultaneously, it integrates magnetic field response stiffness adjustment, adaptive damping control, fault self-diagnosis, and environmental purification functions.

[0058] This invention also includes the following modules:

[0059] The blockchain-based trusted management module establishes a seedling lifecycle management consortium blockchain, employing a Practical Byzantine Fault-Tolerant (PBFT) consensus mechanism. Nodes include seedling planting enterprises, landscaping management departments, and research institutions. A block size of 2MB and a block generation time of 10 seconds are set to ensure the timeliness and consistency of data recording. Smart contracts are designed to define the triggering conditions (accuracy ±0.01) for the reinforcement scheme execution; for example, when the seedling stability coefficient K drops to 0.78, the adjustment program of the intelligent support device is automatically triggered. A hash function (SHA-256) is used to encrypt seedling stability data and reinforcement records, generating a 256-bit hash value to achieve tamper-proof data storage. Simultaneously, zero-knowledge proof technology is used to prevent the leakage of sensitive information during data verification, achieving a verification efficiency of up to 1200 times / second and ensuring data privacy and security. Through blockchain technology, the entire lifecycle of seedlings, from planting, monitoring, reinforcement to maintenance, is traceable and responsibility is determined, improving the transparency and credibility of seedling management.

[0060] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A smart detection and reinforcement decision-making system for seedling fixation stability, characterized in that, Includes the following modules: Multi-source data acquisition module: Deploys a biomimetic distributed sensor network and uses quantum encryption technology to transmit data; it uses a self-organizing network via the ZigBee protocol, with a data transmission frequency of 10Hz and a key update frequency of once per hour; Data preprocessing module: Develops a feature extraction algorithm for seedling physiological signals, separates mechanical vibration and physiological activity signals through wavelet packet decomposition, and fuses sensor data using Kalman filtering to construct a seedling stress-growth coupling model M = α·S. mech +β·S physio +γ·F Kalman M is the output of the coupled model, α and β are the signal weighting coefficients, and S mech Mechanical vibration signal, S physio Physiological activity signal, gamma filter coefficient, F Kalman Kalman filter output; sliding window algorithm is used to smooth time series data and eliminate measurement noise; Stability assessment module: Constructs an ecomechanical assessment model for seedlings, integrating fluid dynamics effects, material nonlinearity, and root fixation field; introduces the stress relaxation coefficient of seedling growth, establishes a time-varying stability assessment model, and sets a safety threshold; Intelligent Decision Module: Constructs a seedling-environment-consolidation co-evolutionary algorithm, integrating genetic algorithm and ant colony algorithm, adopting a multi-objective optimization algorithm, and introducing the co-evolutionary fitness formula F=ω1·f1(x). －1 +ω2·f2(x), where F is the degree of synergy, f1 is the reinforcement cost function, f2 is the expected stable improvement function, and ω1 and ω2 are weight coefficients and ω1+ω2=1; The optimal solution is determined by Pareto optimal solution, and a multi-stage reinforcement strategy is dynamically generated and seasonally adaptively adjusted. Execution control module: Design a shape memory polymer-based intelligent support system, develop photothermal response, self-healing, and biodegradation functions; adopt a magnetorheological elastomer intelligent support device to automatically adjust the support angle and tension.

2. The intelligent detection and reinforcement decision-making system for seedling fixation stability according to claim 1, characterized in that, Also includes: Early warning response module: When the monitoring data triggers the three-level early warning mechanism, the system automatically sends SMS and email notifications, activates emergency support devices, and triggers the emergency response program of the ecological monitoring module.

3. The intelligent detection and reinforcement decision-making system for seedling fixation stability according to claim 1, characterized in that, Also includes: Digital Twin Optimization Module: Establish a three-dimensional mechanical digital twin model of seedlings, solve the dynamic mechanical equations using the meshless Galerkin method, develop a real-time data synchronization protocol, and bidirectionally map the physical entity and the virtual model; optimize the parameters of the digital twin model based on reinforcement learning, and automatically execute the optimized reinforcement scheme through smart contracts.

4. The intelligent detection and reinforcement decision-making system for seedling fixation stability according to claim 1, characterized in that, The stability assessment module introduces a root fixation correction coefficient to correct the stability coefficient calculation under different soil conditions; it also uses viscoelastic mechanics theory combined with stress relaxation effect during seedling growth to predict the evolution of seedling stability.

5. The intelligent detection and reinforcement decision-making system for seedling fixation stability according to claim 1, characterized in that, The intelligent decision-making module constructs a multi-objective game decision-making algorithm that integrates economic costs, ecological impacts, and social benefits, and solves for the optimal strategy combination through Nash equilibrium.

6. The intelligent detection and reinforcement decision-making system for seedling fixation stability according to claim 1, characterized in that, Also includes: Energy self-sustaining module: Develop blade-type triboelectric nanogenerator and seedling transpiration energy harvesting device, and use supercapacitor bank to store energy; By combining a dynamic power management algorithm, the system power consumption is dynamically adjusted according to the sensor sampling frequency.

7. The intelligent detection and reinforcement decision-making system for seedling fixation stability according to claim 1, characterized in that, The multi-source data acquisition module is deployed as a mobile monitoring node on a drone, equipped with lidar and a hyperspectral imager, based on A * The algorithm autonomously plans routes; sensor fusion positioning technology is used to inspect the seedling community and collect data.

8. The intelligent detection and reinforcement decision-making system for seedling fixation stability according to claim 1, characterized in that, Also includes: Bio-mechanical synergistic reinforcement module: Design plant-induced growth scaffolds and regulate plant phototropism through blue LEDs; develop a microbial soil improvement system and inoculate rhizobia and phosphate-solubilizing bacteria; construct a root-support structure mechanical synergistic model to couple and enhance the effects of biological reinforcement and artificial reinforcement.

9. The intelligent detection and reinforcement decision-making system for seedling fixation stability according to claim 1, characterized in that, The execution control module adopts a magnetorheological elastomer intelligent support device, with a built-in piezoelectric sensor array for self-diagnosis of faults, and a photocatalytic coating on the surface.

10. The intelligent detection and reinforcement decision-making system for seedling fixation stability according to claim 1, characterized in that, Also includes: Blockchain Trust Management Module: Establish a seedling lifecycle management alliance chain, design a smart contract automatic execution reinforcement scheme, and store seedling stability data; Zero-knowledge proof technology is used to protect data privacy.

Images