A real-time monitoring system for the growth status of apricot and plum based on sensors

Abstract

The invention relates to the technical field of agricultural production, and in particular to a sensor-based real-time monitoring system for the growth status of apricot and plum. A plurality of sensors are arranged to collect key growth status data in an apricot and plum planting area in real time. A data processing module is used to process the growth status data. A growth model construction module uses a long short-term memory network to construct an apricot and plum growth status prediction model, and predicts the growth trend, health status and potential risks of the apricot and plum in real time. An abnormality detection and early warning module compares the real-time data with the model prediction result, identifies abnormal situations in time and issues an early warning to a user. An irrigation and fertilization decision module generates an optimal irrigation, fertilization and environmental regulation strategy. A control execution module automatically regulates related equipment. A visualization module displays monitoring data, prediction results, early warning information and decision strategies. The invention significantly improves the economic benefits and sustainability of apricot and plum planting.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural production, and in particular to a sensor-based real-time monitoring system for the growth status of apricots and plums. Background Art

[0002] As a fruit with high economic value, the growth of apricot and plum is affected by multiple environmental factors, such as soil moisture, temperature, light intensity, etc. With the development of sensor technology, Internet of Things, big data analysis and artificial intelligence, sensor-based real-time monitoring systems have emerged. By deploying a variety of sensors in apricot and plum planting areas and collecting key environmental data in real time, the growth status of apricot and plum can be accurately monitored, providing scientific and accurate decision support for agricultural managers.

[0003] Although the existing intelligent agricultural monitoring systems can collect a certain amount of growth data and provide preliminary warnings, they still have obvious defects in accuracy, reliability and intelligence. First, the data collection and processing methods of most systems are relatively basic, relying on traditional statistical analysis or simple interpolation methods, which have great limitations when dealing with complex and changeable environmental factors, and cannot effectively capture the potential laws or nonlinear characteristics in the growth status data, resulting in inaccurate data analysis results. Secondly, most of the current growth model construction methods use linear regression or simple models based on experience. These models fail to take into account the complex nonlinear relationship between multiple variables in the growth process of apricots and plums, and cannot accurately predict the health status and growth trend of crops. In addition, the existing decision-making optimization modules usually only consider a single goal, such as irrigation or fertilization, lack a comprehensive optimization method for multiple goals, and cannot balance multiple demands such as water resources, fertilizer application and environmental regulation, which easily leads to resource waste or improper regulation. Summary of the invention

[0004] The invention provides a sensor-based real-time monitoring system for the growth status of apricots and plums.

[0005] A sensor-based real-time monitoring system for the growth status of apricots and plums, comprising a data acquisition module, a data processing module, a growth model building module, an abnormality detection and early warning module, an irrigation and fertilization decision module, a control execution module and a visualization module, wherein;

[0006] The data acquisition module collects growth status data of apricots and plums in real time through a variety of sensors arranged in the apricot and plum planting area, and the growth status data includes soil moisture, ambient temperature, light intensity, trunk diameter change and leaf water potential;

[0007] The data processing module is used to process the collected growth status data, and the processing includes data cleaning, data interpolation, data standardization and feature extraction;

[0008] The growth model building module builds a growth state model of apricot plums based on the processed growth state data using a deep learning algorithm. The growth state model of apricot plums is used to predict the growth trend of apricot plums, evaluate the health status of apricot plums under current environmental conditions, and provide risk warnings;

[0009] The anomaly detection and early warning module compares the prediction results of the apricot and plum growth state model with the real-time data, identifies abnormal conditions in the apricot and plum growth process, and issues early warning information to users in a variety of ways;

[0010] The irrigation and fertilization decision module generates the optimal decision strategy based on the real-time collected growth status data and the analysis results of the apricot and plum growth status model in combination with the multi-objective optimization algorithm. The decision strategy includes irrigation strategy, fertilization strategy and environmental control strategy;

[0011] The control execution module receives the generated decision strategy and automatically controls the irrigation equipment, fertilization equipment and environmental control equipment;

[0012] The visualization module is used to present growth status data, apricot and plum growth status model prediction results, abnormal warning information and decision-making strategies to users in a graphical interface.

[0013] Optionally, the data acquisition module includes:

[0014] Sensor deployment: Multiple sensors are deployed in the apricot and plum planting area. The sensors are arranged according to different growth status data requirements, including soil moisture sensors, ambient temperature sensors, light intensity sensors, trunk diameter change sensors, and leaf water potential sensors;

[0015] Data collection: The growth status data is collected in real time through multiple sensors, and the collected growth status data is transmitted to the data processing module through the wireless communication unit;

[0016] Data synchronization and integration: During the data collection process, the built-in data synchronization unit ensures that the data collected by different sensors remain synchronized in time.

[0017] Optionally, the data processing module includes:

[0018] Data cleaning: During the data collection process, the collected data may be affected by sensor errors or environmental interference, resulting in abnormalities or noise. The abnormal data is identified and deleted using the standard deviation method.

[0019] Data interpolation: For missing data caused by sensor failure or transmission interruption, the data interpolation unit uses linear interpolation to supplement the missing data;

[0020] Data standardization: standardize the collected data so that different data have the same dimension and range;

[0021] Feature extraction: The data processing module analyzes the cleaned, interpolated and standardized data to extract the most critical features for predicting the growth status of apricots and plums, including soil moisture fluctuations, daily changes in light intensity and trunk diameter growth rate.

[0022] Optionally, the growth model building module includes:

[0023] Data preparation: Prepare historical growth status data and divide the historical growth status data into training set and validation set;

[0024] Model construction: A growth status model of apricot and plum was constructed based on the long short-term memory network algorithm to predict the growth trend and health status of apricot and plum;

[0025] Model training and optimization: Using the training set data, the back propagation algorithm and optimization algorithm (such as Adam optimizer) are used to train the growth state model of apricot and plum;

[0026] Model evaluation: After training, the model is evaluated using the validation set data. Evaluation indicators include prediction error, mean square error, and accuracy.

[0027] Optionally, the growth model building module further includes:

[0028] Growth trend prediction: Based on the trained growth status model of apricot and plum, the future growth trend of apricot and plum is predicted according to the real-time collected growth status data;

[0029] Health status assessment: The apricot and plum growth status model assesses the health status of apricots and plums based on real-time growth status data and growth trend prediction results.

[0030] Risk warning: Based on the health status assessment results, the growth model construction module provides risk warnings that may exist during the growth of apricots and plums.

[0031] Optionally, the anomaly detection and early warning module includes:

[0032] Comparison of prediction results with real-time data: The anomaly detection and early warning module receives the prediction results of the apricot and plum growth status model (including the growth trend, health status, trunk diameter change, leaf water potential change, etc. of the apricot and plum), as well as the real-time collected growth status data (including soil moisture, ambient temperature, light intensity, etc.);

[0033] By setting a predetermined threshold, the predicted results are compared with the real-time growth status data item by item for each growth status feature (such as soil moisture, leaf water potential, etc.);

[0034] Anomaly detection algorithm: After comparison, the anomaly detection and early warning module uses anomaly detection algorithm to identify abnormal conditions in the growth process of apricots and plums.

[0035] Threshold setting and dynamic adjustment: In the anomaly detection module, the predetermined threshold is set based on historical growth status data and dynamically adjusted to adapt to different stages of the apricot and plum growth cycle;

[0036] Abnormal identification and warning triggering: If abnormal conditions are identified in the growth process of apricots and plums, different levels of warning information will be issued to users according to the type and severity of the abnormality;

[0037] Abnormal warning level and response strategy: The abnormal warning module sets different warning levels for each abnormality according to the severity of the detected abnormality.

[0038] Optionally, the irrigation and fertilization decision module generates an optimal decision strategy based on the real-time collected growth status data and the analysis results of the apricot and plum growth status model in combination with a particle swarm optimization algorithm, including:

[0039] Real-time growth status data reception: The irrigation and fertilization decision module receives the real-time growth status data from the data acquisition module. The real-time growth status data provides basic environmental information on the current growth of apricots and plums for decision making;

[0040] Receiving the analysis results of the growth status model: The irrigation and fertilization decision module receives the prediction results of the apricot and plum growth status model.

[0041] Particle swarm optimization algorithm: The irrigation and fertilization decision module uses particle swarm optimization algorithm to solve multiple optimization objectives, including irrigation strategy, fertilization strategy and environmental control strategy;

[0042] Generate the optimal decision strategy: solve the optimization target through the particle swarm optimization algorithm to obtain the optimal decision strategy;

[0043] Decision strategy implementation: The irrigation and fertilization decision module passes the generated optimal decision strategy to the control execution module.

[0044] Optionally, the control execution module includes:

[0045] Receiving irrigation and fertilization strategy instructions: the control execution module receives the optimal decision strategy generated by the irrigation and fertilization decision module;

[0046] Instruction parsing and processing: The control execution module parses the received optimal decision strategy and generates irrigation strategy, fertilization strategy and environmental control strategy;

[0047] Control signal generation and transmission: The control execution module generates corresponding control signals according to the analyzed irrigation strategy, fertilization strategy and environmental control strategy;

[0048] Control device execution instructions: The control execution module transmits the generated control signals to each execution device through the communication interface with the irrigation equipment, fertilization equipment and environmental control equipment.

[0049] Optionally, the visualization module includes:

[0050] Data reception and integration: receiving real-time collected growth status data, prediction results of the apricot and plum growth status model, abnormal warning information generated by the abnormal detection and warning module, and the optimal decision-making strategy;

[0051] Graphical interface: The visualization module designs and generates a variety of graphical interfaces to display growth status data, prediction results of apricot and plum growth status models, abnormal warning information, and decision-making strategies;

[0052] Interactive operation and dynamic feedback: The visualization module supports interactive operation. Users can click or drag graphic elements (such as sliders, buttons, switching charts, etc.) on the interface to adjust the displayed content as needed.

[0053] Data export and report generation: The visualization module supports data export and report generation functions, allowing users to export displayed growth status data, forecast results, warning information and decision strategies into standard formats (such as CSV, PDF, etc.) for subsequent analysis, archiving or report writing.

[0054] Beneficial effects of the present invention:

[0055] The present invention collects key data of the growth status of apricot and plum in real time (such as soil moisture, ambient temperature, light intensity, trunk diameter change and leaf water potential) through the deployment of multiple sensors, and cleans, interpolates, standardizes and extracts features of the collected data in combination with the data processing module, thereby ensuring the accuracy and integrity of the data. The growth model construction module uses the long short-term memory network algorithm to establish an apricot and plum growth status model, which can accurately predict the growth trend of apricot and plum, dynamically evaluate the health status and identify potential risks. This multi-level and multi-angle monitoring and analysis method significantly improves the data utilization efficiency in the apricot and plum planting process, and provides a reliable basis for scientific decision-making.

[0056] The present invention, through the irrigation and fertilization decision module, combined with the particle swarm optimization algorithm, integrates the real-time data and the prediction results of the growth state model to formulate the optimal irrigation, fertilization and environmental control strategy. This multi-objective optimization algorithm can find the best balance between water resource utilization, fertilizer application efficiency and environmental load, and effectively avoid resource waste or environmental pollution caused by excessive irrigation or fertilization. In addition, the control execution module realizes the automatic and precise control of irrigation equipment, fertilization equipment and environmental control equipment, ensures the efficient execution of the strategy, and significantly improves the economic benefits and sustainability of apricot and plum planting. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;

[0059] Figure 2 It is a schematic diagram of the growth model construction module flow in an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0061] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0062] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0063] like Figure 1-Figure 2 As shown, a sensor-based real-time monitoring system for the growth status of apricots and plums includes a data acquisition module, a data processing module, a growth model building module, an abnormality detection and early warning module, an irrigation and fertilization decision module, a control execution module and a visualization module, wherein;

[0064] The data acquisition module collects real-time growth data of apricot and plum trees through various sensors deployed in the apricot and plum planting area. The growth data includes soil moisture, ambient temperature, light intensity, trunk diameter changes, and leaf water potential.

[0065] The data processing module is used to process the collected growth status data, including data cleaning, data interpolation, data standardization and feature extraction;

[0066] The growth model building module builds a growth state model of apricot and plum based on the processed growth state data using a deep learning algorithm. The growth state model of apricot and plum is used to predict the growth trend of apricot and plum, evaluate the health status of apricot and plum under current environmental conditions, and provide risk warnings.

[0067] The anomaly detection and early warning module compares the prediction results of the apricot and plum growth status model with real-time data, identifies abnormal conditions in the apricot and plum growth process, and issues early warning information to users in a variety of ways;

[0068] The irrigation and fertilization decision module generates the optimal decision strategy based on the real-time collected growth status data and the analysis results of the apricot and plum growth status model, combined with the multi-objective optimization algorithm. The decision strategy includes irrigation strategy, fertilization strategy and environmental control strategy;

[0069] The control execution module receives the generated decision strategy and automatically controls the irrigation equipment, fertilization equipment and environmental control equipment;

[0070] The visualization module is used to present growth status data, apricot and plum growth status model prediction results, abnormal warning information and decision-making strategies to users in a graphical interface.

[0071] The data acquisition module includes:

[0072] Sensor deployment: Multiple sensors are deployed in the apricot and plum planting area. The sensors are arranged according to different growth status data requirements, including soil moisture sensors, ambient temperature sensors, light intensity sensors, trunk diameter change sensors and leaf water potential sensors, among which;

[0073] Soil moisture sensors are used to monitor the moisture content of the soil in the apricot and plum root areas;

[0074] The ambient temperature sensor is used to monitor the temperature of the air around the apricot and plum trees to ensure the impact of environmental conditions on growth;

[0075] The light intensity sensor is used to monitor the light intensity around the apricot and plum trees and evaluate the effectiveness of photosynthesis;

[0076] The trunk diameter change sensor is installed in the middle of the apricot plum tree trunk to monitor the change of the trunk diameter to reflect the growth rate of the apricot plum;

[0077] Leaf water potential sensors are non-invasively installed on apricot and plum leaves to monitor leaf water stress;

[0078] Data collection: The growth status data is collected in real time through multiple sensors, and the collected growth status data is transmitted to the data processing module through the wireless communication unit. The specific collection content includes:

[0079] Soil moisture: monitors the amount of water in the soil, usually expressed as a percentage;

[0080] Ambient temperature: Record the temperature of the surrounding air in degrees Celsius;

[0081] Light intensity: Record the ambient light intensity in Lux;

[0082] Change in trunk diameter: The change in trunk diameter was recorded in millimeters;

[0083] Leaf water potential: The degree of leaf water stress is recorded in megapascals (MPa);

[0084] Data synchronization and integration: During the data collection process, the built-in data synchronization unit ensures that the data collected by different sensors are synchronized in time to facilitate subsequent processing and analysis, avoiding data errors caused by data delay or asynchrony;

[0085] The data acquisition module deploys a variety of sensors to accurately monitor the most critical status parameters in the growth process of apricots and plums, ensuring the real-time and accuracy of the data. This provides a solid foundation for subsequent data processing, model building, anomaly detection and decision support, and improves the intelligence and reliability of the system.

[0086] The data processing module includes:

[0087] Data cleaning: During the data collection process, the collected data may be affected by sensor errors or environmental interference, resulting in abnormalities or noise. The abnormal data is identified and deleted using the standard deviation method.

[0088] Standard deviation method: Assume that the collected data conforms to the normal distribution. First, calculate the mean μ and standard deviation σ of the data set. For each data point x i , if its deviation from the mean exceeds the specified multiple of the standard deviation, that is:

[0089] |x i -μ|>kσ, (where k is a preset threshold, usually 2 or 3);

[0090] The data point is considered to be an outlier;

[0091] The cleaned data will be marked as valid data to ensure that it is not affected by noise in subsequent analysis;

[0092] Data interpolation: For missing data caused by sensor failure or transmission interruption, the data interpolation unit uses linear interpolation to supplement the missing data and maintain data continuity;

[0093] Linear interpolation: For missing values ​​x t , using the data x at adjacent times t-1 and x t+1 Calculate the interpolation, expressed as:

[0094]

[0095] Data standardization: Standardize the collected data so that different data have the same dimension and range to ensure that all types of data can be compared on the same scale, expressed as:

[0096]

[0097] Among them, x is the original data, μ is the mean of the data, σ is the standard deviation of the data, and x ′ is the standardized data;

[0098] The standardized data can eliminate the dimensional differences between different features, ensuring that each data has the same weight in subsequent processing and analysis;

[0099] Feature extraction: The data processing module extracts the most critical features for predicting the growth status of apricots and plums by analyzing the cleaned, interpolated and standardized data, including soil moisture fluctuations, daily changes in light intensity and trunk diameter growth rate. The feature extraction methods include:

[0100] Time series feature extraction: extract statistical features such as maximum value, minimum value, mean value, variance, etc. from sensor data;

[0101] Trend analysis: By calculating the slope of data changes, the characteristics reflecting the rate of change of growth status are extracted;

[0102] Periodic feature extraction: For features with periodic changes (such as light intensity), extract periodic information for subsequent model training.

[0103] Growth model building blocks include:

[0104] Data preparation: Prepare historical growth status data and divide the historical growth status data into training set and validation set;

[0105] Model construction: Based on the long short-term memory network algorithm, a growth state model of apricot and plum is constructed to predict the growth trend and health status of apricot and plum. The growth state model of apricot and plum includes an input layer, multiple long short-term memory network layers, a fully connected layer and an output layer, among which;

[0106] Input layer: receives processed growth status characteristic data, such as soil moisture, ambient temperature, light intensity, trunk diameter change, and leaf water potential;

[0107] Long short-term memory network layer: contains multiple long short-term memory network units, which are used to learn the temporal features in the input data;

[0108] Fully connected layer: connects the long short-term memory network layer and the output layer to extract deep features and perform comprehensive evaluation;

[0109] Output layer: outputs the predicted values ​​of the growth status of apricots and plums, such as growth trend, health status score, etc.

[0110] Model training and optimization: Using the training set data, the back propagation algorithm and optimization algorithm (such as Adam optimizer) are used to train the growth state model of apricot and plum. The mean square error is used as the loss function during the training process to ensure that the model can accurately predict the growth trend of apricot and plum.

[0111] The model continuously reduces the prediction error by adjusting the network weights to improve its prediction accuracy;

[0112] Model evaluation: After training, the model is evaluated using validation set data to check the generalization ability and accuracy of the apricot and plum growth status model. The evaluation indicators include prediction error, mean square error, and accuracy.

[0113] The growth model building module also includes:

[0114] Growth trend prediction: Based on the trained apricot and plum growth status model and the real-time collected growth status data, the future growth trend of apricot and plum is predicted. The specific steps are as follows:

[0115] By inputting real-time growth status data into the trained apricot plum growth status model, the apricot plum growth status model will output the growth trend of apricot plum in the future, including changes in trunk diameter, leaf water potential and soil moisture.

[0116] Based on the model output, predict the health status of the apricot plum, such as accelerated growth, normal growth, or restricted growth;

[0117] Health status assessment: The apricot and plum growth status model assesses the health status of apricot and plum based on real-time growth status data and growth trend prediction results. The specific assessment methods include:

[0118] Growth index: Based on the growth rate, trunk diameter, leaf water potential and other indicators of the apricot plum, the growth index is calculated to quantify the health status of the apricot plum;

[0119] Abnormal score: Based on the comparison between historical growth status data and real-time growth status data, it is evaluated whether the apricot and plum are in an abnormal growth state. If the growth state deviates from the normal range, the apricot and plum growth status model outputs an abnormal score and provides health warning information.

[0120] Risk warning: Based on the health status assessment results, the growth model construction module provides risk warnings that may exist during the growth of apricots and plums. The basis for risk warnings includes:

[0121] Changes in meteorological conditions: such as sudden rise or fall in temperature, insufficient sunlight, etc.;

[0122] Extreme changes in soil moisture: such as too dry or too wet;

[0123] Stagnation of trunk diameter growth: If the rate of change in trunk diameter is lower than a certain threshold, it means that the tree may be in a growth bottleneck period or affected by physiological disorders.

[0124] The anomaly detection and warning module includes:

[0125] Comparison of prediction results with real-time data: The anomaly detection and early warning module receives the prediction results of the apricot and plum growth status model (including the growth trend, health status, trunk diameter change, leaf water potential change, etc. of the apricot and plum), as well as the real-time collected growth status data (including soil moisture, ambient temperature, light intensity, etc.);

[0126] By setting a predetermined threshold, for each growth status feature (such as soil moisture, leaf water potential, etc.), the predicted results are compared with the real-time growth status data item by item. The specific steps are as follows:

[0127] Error calculation: For each feature, calculate the difference (error) between the predicted result and the real-time collected data, for example:

[0128] Error = |x 实时 -x 预测 |;

[0129] Among them, x 实时 is real-time data, x 预测 Predict results for the model;

[0130] Anomaly detection algorithm: After comparison, the anomaly detection and warning module uses anomaly detection algorithms to identify abnormal conditions in the growth process of apricots and plums, including:

[0131] Error-based anomaly detection: For each feature, if the error exceeds the set threshold (for example, the error is greater than a certain set value), the feature is considered to be abnormal. For example, for soil moisture, if the error between the real-time soil moisture value and the predicted value is greater than the predetermined tolerance range, the soil moisture is considered to be abnormal.

[0132] Multivariate joint detection: The comparison results of multiple features are integrated. If multiple features (such as soil moisture, ambient temperature, leaf water potential, etc.) are abnormal at the same time, it means that there may be systemic growth problems in the apricots and plums. At this time, the abnormal information of these features will be combined for joint judgment to further improve the accuracy of anomaly detection.

[0133] Threshold setting and dynamic adjustment: In the anomaly detection module, the preset threshold is set based on the historical growth status data, and dynamically adjusted to adapt to the different stages of the growth cycle of apricot plums. For example, in the early growth period of apricot plums, the trunk diameter and leaf water potential change slowly, so a looser threshold may be set. In the vigorous growth period, if these characteristics change too quickly, it is considered that there may be anomalies.

[0134] Dynamic adjustment mechanism: Automatically adjust the warning threshold according to the changing trend of real-time growth status data to ensure effective identification of anomalies at different growth stages;

[0135] Abnormal identification and warning triggering: If abnormal conditions are identified during the growth of apricots and plums, different levels of warning information will be issued to users based on the type and severity of the abnormality. The warning information will be notified in the following ways:

[0136] SMS / email warning: abnormal warnings can be sent to users via SMS or email, detailing the abnormal type, occurrence time and possible causes;

[0137] Real-time APP notification: Users can receive real-time warning information about abnormal growth status of apricots and plums through the mobile application. The APP will push abnormal notifications and provide detailed analysis reports;

[0138] Abnormal warning level and response strategy: The abnormal warning module sets different warning levels for each abnormality according to the severity of the detected abnormality. The warning levels are as follows:

[0139] Mild warning: Warning information reminds users that the growth status deviates from normal, but it does not affect the overall health of the apricots and plums. Users can adjust management strategies based on the prompts;

[0140] Moderate warning: Warning information reminds users that there is a large deviation in the growth status, and the growth of apricots and plums may be affected. Users are advised to take intervention measures, such as adjusting irrigation or fertilization strategies;

[0141] Serious warning: Warning information reminds users that the growth of apricots and plums is seriously abnormal, which may cause health damage or loss. The system will recommend immediate measures (such as irrigation, fertilization or environmental control).

[0142] The irrigation and fertilization decision module generates the optimal decision strategy based on the real-time collected growth status data and the analysis results of the apricot and plum growth status model, combined with the particle swarm optimization algorithm, including:

[0143] Real-time growth status data reception: The irrigation and fertilization decision module receives the real-time growth status data from the data acquisition module. The real-time growth status data provides basic environmental information on the current growth of apricots and plums for decision making;

[0144] Receiving the analysis results of the growth status model: The irrigation and fertilization decision module receives the prediction results of the apricot and plum growth status model, including the future growth trend, health status and potential risks of apricot and plum. The output of the model can provide prediction information for irrigation and fertilization decisions and guide optimization decisions.

[0145] Particle swarm optimization algorithm: The irrigation and fertilization decision module uses the particle swarm optimization algorithm to solve multiple optimization objectives. The particle swarm optimization algorithm is an optimization algorithm that simulates the foraging behavior of bird flocks and is suitable for solving global optimization problems in continuous space. In this module, the optimization objectives of the particle swarm optimization algorithm include irrigation strategy, fertilization strategy, and environmental control strategy. The optimal decision is generated by optimizing the following objective functions:

[0146] Irrigation objective function: Optimize irrigation amount to ensure that soil moisture remains within a suitable range and avoid over-irrigation or under-irrigation. The objective function is defined as:

[0147] f 灌溉 =min(|M 土壤湿度 -M 目标湿度 |);

[0148] Among them, M 土壤湿度 is the real-time soil moisture data, M 目标湿度 is the predetermined soil moisture target value;

[0149] Fertilization objective function: Minimize the amount of fertilizer applied while ensuring that the nutritional needs of apricots and plums are met. The objective function is defined as:

[0150] f 施肥 =min(|C 施肥量 -C 施肥需求 |);

[0151] Among them, C 施肥量 is the current fertilizer application amount, C 施肥需求 The fertilizer demand is estimated based on the growth state model of apricot and plum and environmental conditions;

[0152] Environmental control objective function: Optimize environmental control measures (such as temperature control, light control, etc.) to ensure that apricots and plums grow under the best environmental conditions. The objective function is defined as:

[0153] f 环境调控 =min(E 能源消耗 +P 环境负荷 );

[0154] Among them, E 能源消耗 For energy consumption of control measures, P 环境负荷 For environmental load, the goal is to minimize the energy and costs of environmental regulation;

[0155] The implementation process of the particle swarm optimization algorithm includes:

[0156] The particle swarm optimization algorithm searches the solution space through a group of "particles", each particle represents a potential decision-making plan (including irrigation amount, fertilization amount and environmental control measures). Each particle updates its position iteratively and searches for the optimal solution based on the fitness function (i.e. the above objective function). The specific steps are as follows:

[0157] Initialize the particle swarm: Each particle is randomly initialized to a possible decision vector, representing a set of initial strategies for irrigation, fertilization, and environmental regulation;

[0158] Calculate particle fitness: Calculate the fitness value of each particle, that is, the objective function value (such as the error or cost of irrigation, fertilization and environmental regulation);

[0159] Update particle speed and position: According to the particle's current speed, historical best position, and global best position, the particle's speed and position are updated using the following formula;

[0160] Generate the optimal decision strategy: Solve the optimization target through the particle swarm optimization algorithm to obtain the optimal decision strategy, which includes:

[0161] Optimal irrigation strategy: Determine the irrigation amount and timing based on the optimal solution to ensure that soil moisture is within the target range;

[0162] Optimal fertilization strategy: Determine the amount and type of fertilizer based on the optimal solution to ensure that the nutritional needs of apricots and plums are met;

[0163] Optimal environmental control strategy: Determine whether to adjust environmental factors such as temperature and light based on the optimal solution to ensure that apricots and plums grow in the best environment;

[0164] Decision strategy implementation: The irrigation and fertilization decision module passes the generated optimal decision strategy to the control execution module.

[0165] The control execution module includes:

[0166] Receiving irrigation and fertilization strategy instructions: the control execution module receives the optimal decision strategy generated by the irrigation and fertilization decision module;

[0167] Instruction parsing and processing: The control execution module parses the received optimal decision strategy and generates irrigation strategy, fertilization strategy and environmental control strategy. The parsing process includes:

[0168] Instruction format identification: First, identify the format of the decision strategy and confirm the effectiveness and completeness of the decision strategy. The decision strategy format includes but is not limited to the irrigation amount, fertilizer amount, fertilizer type, and the start time of the control equipment;

[0169] Data verification: Verify the numerical data in the decision-making strategy to ensure that it is within a reasonable range. For example, the irrigation amount should not exceed the maximum water volume, and the fertilizer amount should not exceed the soil carrying capacity.

[0170] Control signal generation and transmission: The control execution module generates corresponding control signals according to the analyzed irrigation strategy, fertilization strategy and environmental control strategy. Each device (such as irrigation equipment, fertilization equipment and environmental control equipment) needs to receive specific control signals according to the strategy instructions. The control signals include:

[0171] Irrigation control signal: Generates the opening and closing signals of irrigation equipment and the instructions for adjusting the irrigation amount according to the irrigation strategy;

[0172] Fertilization control signal: Generates the start and stop signals of the fertilization equipment and the instructions for adjusting the amount and type of fertilizer according to the fertilization strategy;

[0173] Environmental control signal: Generates the on / off signals of environmental control equipment (such as temperature control equipment, light control equipment, etc.) and instructions for adjusting parameters (such as temperature, humidity, light intensity, etc.) according to the environmental control strategy;

[0174] Control device execution instructions: The control execution module transmits the generated control signal to each execution device through the communication interface with the irrigation equipment, fertilization equipment and environmental control equipment. After each device receives the control signal, it performs the corresponding operation according to the instruction, for example:

[0175] Irrigation equipment: automatically start or stop irrigation according to control signals, and adjust irrigation volume and irrigation time;

[0176] Fertilization equipment: automatically start fertilization according to control signals, and adjust the amount and method of fertilization (such as liquid fertilization, solid fertilization, etc.);

[0177] Environmental control equipment: adjusts environmental parameters such as temperature, humidity or light according to control signals to ensure that the growth environment of apricots and plums remains in an ideal state.

[0178] The visualization modules include:

[0179] Data reception and integration: receiving real-time collected growth status data, prediction results of the apricot and plum growth status model, abnormal warning information generated by the abnormal detection and warning module, and the optimal decision-making strategy;

[0180] Graphical interface: The visualization module designs and generates a variety of graphical interfaces to display growth status data, apricot and plum growth status model prediction results, abnormal warning information and decision-making strategies, including:

[0181] Real-time growth status data display: Real-time display of soil moisture, ambient temperature, light intensity and other data through line charts, bar charts or dashboards to help users understand the current growth status of apricots and plums;

[0182] Growth trend forecast result display: Display the future growth trend and health assessment of apricots and plums through trend charts or forecast curves, and intuitively display the future growth status, yield forecast, etc.

[0183] Abnormal warning information display: Through color coding, warning icons or dynamic prompt boxes, possible abnormal conditions in the growth process of apricots and plums (such as low soil moisture, insufficient light, etc.) are displayed to users, reminding them to take timely actions;

[0184] Decision strategy display: The generated irrigation, fertilization and environmental control strategies are displayed through pie charts, bar charts or flow charts. Users can view the specific content and implementation status of each strategy, such as irrigation amount, fertilization time, temperature control parameters, etc.

[0185] Interactive operation and dynamic feedback: The visualization module supports interactive operation. Users can click or drag graphic elements (such as sliders, buttons, switching charts, etc.) on the interface to adjust the displayed content as needed.

[0186] Data export and report generation: The visualization module supports data export and report generation functions, allowing users to export displayed growth status data, forecast results, warning information and decision strategies into standard formats (such as CSV, PDF, etc.) for subsequent analysis, archiving or report writing.

[0187] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0188] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A sensor-based real-time monitoring system for the growth status of apricots and plums, characterized in that: It includes data acquisition module, data processing module, growth model building module, anomaly detection and early warning module, irrigation and fertilization decision module, control execution module and visualization module, among which; The data acquisition module collects growth status data of apricots and plums in real time through a variety of sensors arranged in the apricot and plum planting area, and the growth status data includes soil moisture, ambient temperature, light intensity, trunk diameter change and leaf water potential; The data processing module is used to process the collected growth status data, and the processing includes data cleaning, data interpolation, data standardization and feature extraction; The growth model building module builds a growth state model of apricot plums based on the processed growth state data using a deep learning algorithm. The growth state model of apricot plums is used to predict the growth trend of apricot plums, evaluate the health status of apricot plums under current environmental conditions, and provide risk warnings; The anomaly detection and early warning module compares the prediction results of the apricot and plum growth state model with the real-time data, identifies abnormal conditions in the apricot and plum growth process, and issues early warning information to users in a variety of ways; The irrigation and fertilization decision module generates the optimal decision strategy based on the real-time collected growth status data and the analysis results of the apricot and plum growth status model in combination with the multi-objective optimization algorithm. The decision strategy includes irrigation strategy, fertilization strategy and environmental control strategy; The control execution module receives the generated decision strategy and automatically controls the irrigation equipment, fertilization equipment and environmental control equipment; The visualization module is used to present growth status data, apricot and plum growth status model prediction results, abnormal warning information and decision-making strategies to users in a graphical interface.

2. A sensor-based real-time monitoring system for growth status of apricot and plum according to claim 1, characterized in that: The data acquisition module comprises: Sensor deployment: Multiple sensors are deployed in the apricot and plum planting area. The sensors are arranged according to different growth status data requirements, including soil moisture sensors, ambient temperature sensors, light intensity sensors, trunk diameter change sensors, and leaf water potential sensors; Data collection: The growth status data is collected in real time through multiple sensors, and the collected growth status data is transmitted to the data processing module through the wireless communication unit; Data synchronization and integration: During the data collection process, the built-in data synchronization unit ensures that the data collected by different sensors remain synchronized in time.

3. A sensor-based real-time monitoring system for growth status of apricot and plum according to claim 2, characterized in that: The data processing module comprises: Data cleaning: During the data collection process, the collected data may be affected by sensor errors or environmental interference, resulting in abnormalities or noise. The abnormal data is identified and deleted using the standard deviation method. Data interpolation: For missing data caused by sensor failure or transmission interruption, the data interpolation unit uses linear interpolation to supplement the missing data; Data standardization: standardize the collected data so that different data have the same dimension and range; Feature extraction: The data processing module analyzes the cleaned, interpolated and standardized data to extract the most critical features for predicting the growth status of apricots and plums, including soil moisture fluctuations, daily changes in light intensity and trunk diameter growth rate.

4. A sensor-based real-time monitoring system for growth status of apricot and plum according to claim 3, characterized in that: The growth model building module includes: Data preparation: Prepare historical growth status data and divide the historical growth status data into training set and validation set; Model construction: A growth status model of apricot and plum was constructed based on the long short-term memory network algorithm to predict the growth trend and health status of apricot and plum; Model training and optimization: Using the training set data, the back propagation algorithm and optimization algorithm are used to train the growth state model of apricot and plum; Model evaluation: After training, the model is evaluated using the validation set data. Evaluation indicators include prediction error, mean square error, and accuracy.

5. A sensor-based real-time monitoring system for growth status of apricot and plum according to claim 4, characterized in that: The growth model building module also includes: Growth trend prediction: Based on the trained growth status model of apricot and plum, the future growth trend of apricot and plum is predicted according to the real-time collected growth status data; Health status assessment: The apricot and plum growth status model assesses the health status of apricots and plums based on real-time growth status data and growth trend prediction results; Risk warning: Based on the health status assessment results, the growth model construction module provides risk warnings in the growth process of apricots and plums.

6. A sensor-based real-time monitoring system for growth status of apricot and plum according to claim 5, characterized in that: The anomaly detection and early warning module includes: Comparison of prediction results and real-time data: The anomaly detection and early warning module receives the prediction results of the apricot and plum growth status model and the real-time collected growth status data; By setting a predetermined threshold, the prediction result is compared with the real-time growth status data item by item for each growth status feature; Anomaly detection algorithm: After comparison, the anomaly detection and early warning module uses anomaly detection algorithms to identify abnormalities in the growth process of apricots and plums; Threshold setting and dynamic adjustment: In the anomaly detection module, the predetermined threshold is set based on historical growth status data and dynamically adjusted to adapt to different stages of the apricot and plum growth cycle; Abnormal identification and warning triggering: If abnormal conditions are identified in the growth process of apricots and plums, different levels of warning information will be issued to users according to the type and severity of the abnormality; Abnormal warning level and response strategy: The abnormal warning module sets different warning levels for each abnormality according to the severity of the detected abnormality.

7. A sensor-based real-time monitoring system for growth status of apricot and plum according to claim 6, characterized in that: The irrigation and fertilization decision module generates the optimal decision strategy based on the real-time collected growth status data and the analysis results of the apricot and plum growth status model combined with the particle swarm optimization algorithm, including: Real-time growth status data reception: The irrigation and fertilization decision module receives the real-time growth status data from the data acquisition module; Receiving the analysis results of the growth status model: The irrigation and fertilization decision module receives the prediction results of the growth status model of apricot and plum; Particle swarm optimization algorithm: The irrigation and fertilization decision module uses particle swarm optimization algorithm to solve multiple optimization objectives, including irrigation strategy, fertilization strategy and environmental control strategy; Generate the optimal decision strategy: solve the optimization target through the particle swarm optimization algorithm to obtain the optimal decision strategy; Decision strategy implementation: The irrigation and fertilization decision module passes the generated optimal decision strategy to the control execution module.

8. A sensor-based real-time monitoring system for growth status of apricot and plum according to claim 7, characterized in that: The control execution module includes: Receiving irrigation and fertilization strategy instructions: the control execution module receives the optimal decision strategy generated by the irrigation and fertilization decision module; Instruction parsing and processing: The control execution module parses the received optimal decision strategy and generates irrigation strategy, fertilization strategy and environmental control strategy; Control signal generation and transmission: The control execution module generates corresponding control signals according to the analyzed irrigation strategy, fertilization strategy and environmental control strategy; Control device execution instructions: The control execution module transmits the generated control signals to each execution device through the communication interface with the irrigation equipment, fertilization equipment and environmental control equipment.

9. A sensor-based real-time monitoring system for growth status of apricot and plum according to claim 8, characterized in that: The visualization module comprises: Data reception and integration: receiving real-time collected growth status data, prediction results of the apricot and plum growth status model, abnormal warning information generated by the abnormal detection and warning module, and the optimal decision-making strategy; Graphical interface: The visualization module designs and generates a variety of graphical interfaces to display growth status data, prediction results of apricot and plum growth status models, abnormal warning information, and decision-making strategies; Interactive operation: The visualization module supports interactive operation. Users can click or drag graphic elements on the interface to adjust the displayed content as needed. Data export and report generation: The visualization module supports data export and report generation functions, allowing users to export displayed growth status data, forecast results, warning information and decision strategies into a standard format.

Images