Landscaping plant maintenance drip irrigation device and use method thereof

The landscaping drip irrigation device, which combines image acquisition and machine learning, solves the problems of dripper clogging and high cost, and achieves precise drip irrigation and automated management, thereby improving agricultural production efficiency and water resource utilization.

CN118947519AInactive Publication Date: 2024-11-15临沂市园林环卫保障服务中心
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411392669.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-08
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing drip irrigation technology suffers from problems such as dripper clogging, high initial investment costs, and high maintenance requirements, which affect irrigation uniformity and economic benefits.

Method used

The system uses an image acquisition module to obtain plant information, combines it with environmental data for precise drip irrigation, utilizes a machine learning model to monitor equipment status in real time, predicts faults and provides maintenance suggestions, and integrates a rainwater harvesting system and intelligent control valves to achieve automated drip irrigation.

Benefits of technology

It has achieved precise and efficient drip irrigation, reduced manual labor, saved water resources, and improved agricultural management efficiency and economic benefits.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118947519A_ABST
    Figure CN118947519A_ABST
Patent Text Reader

Abstract

The invention provides a landscaping plant maintenance drip irrigation device and a use method thereof, and relates to the technical field of agriculture, and the landscaping plant maintenance drip irrigation device comprises the following modules: an image acquisition module which is composed of a plurality of cameras and is used for obtaining initial and current plant image information of landscaping plants; the environment data acquisition module is used for acquiring environment data, wherein the environment data comprises illumination intensity and duration time; the data storage module is used for recording and storing plant image information, transpiration data and environment data; the data processing module is responsible for plant image information analysis, transpiration calculation and drip irrigation water consumption calculation; the control execution module controls the operation of the drip irrigation system according to the calculation result; the drip irrigation execution module comprises a water source, a water conveying pipe network and a water dropper and is used for achieving accurate drip irrigation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of agriculture, and in particular to a drip irrigation device for maintaining garden plants and a method for using the device. Background Art

[0002] Although drip irrigation technology has significant advantages in improving water resource utilization efficiency and crop yields, there are still some problems. The following are the main challenges faced by existing drip irrigation technology: Dripper clogging: This is one of the most common problems with drip irrigation systems. Reasons include impurities in the water, mineral deposition, algae growth, etc. Clogging can lead to uneven irrigation and affect crop growth. High initial investment cost: Installing a drip irrigation system requires a large upfront investment. It can be a financial burden for small-scale farmers. High maintenance requirements: The system needs to be inspected and cleaned regularly. This includes cleaning filters, inspecting and replacing damaged drippers, etc.

[0003] In view of this, the present invention proposes a gardening plant maintenance drip irrigation device and a method of using the same. Summary of the invention

[0004] The main purpose of the present invention is to provide a drip irrigation device for maintaining garden plants and a method of using the same. To achieve the above purpose, the technical solution includes the following aspects.

[0005] According to one aspect of an embodiment of the present application, a drip irrigation device for maintaining garden plants is provided, comprising the following modules:

[0006] Image acquisition module: composed of multiple cameras, used to obtain the initial and current plant image information of garden greening plants;

[0007] Environmental data acquisition module: used to obtain environmental data, including light intensity and duration;

[0008] Data storage module: used to record and store plant image information, transpiration data and environmental data;

[0009] Data processing module: responsible for plant image information analysis, transpiration calculation and drip irrigation water consumption calculation;

[0010] Control execution module: controls the operation of the drip irrigation system according to the calculation results;

[0011] Drip irrigation execution module: including water source, water pipe network and dripper, used to achieve precise drip irrigation;

[0012] Equipment detection module: uses machine learning models to monitor the working status of drip irrigation equipment in real time;

[0013] According to one aspect of an embodiment of the present application, the device detection module includes:

[0014] Data acquisition unit: collects real-time data from pressure sensors and flow meters;

[0015] Machine learning model: A model trained based on historical data to analyze the working status of equipment;

[0016] Anomaly detection algorithms: used to identify potential equipment failures or blockages;

[0017] Predictive maintenance unit: predicts possible problems and makes maintenance recommendations based on test results;

[0018] Human-computer interaction interface: used to display test results and maintenance suggestions, and allow manual intervention.

[0019] According to one aspect of an embodiment of the present application, the training process of the machine learning model includes:

[0020] Collect historical data under normal working conditions, including water pressure and flow;

[0021] Simulate different types of equipment failures and blockages and collect corresponding abnormal data;

[0022] Use the collected data to train a machine learning model, such as a support vector machine or a deep neural network;

[0023] Optimize model parameters through cross-validation to improve model accuracy and generalization ability;

[0024] Test and fine-tune the model in the actual operating environment to ensure its adaptability.

[0025] According to one aspect of the embodiment of the present application,

[0026] The anomaly detection algorithm includes:

[0027] Real-time data preprocessing: noise reduction and standardization of collected data;

[0028] Multi-parameter joint analysis: comprehensive consideration of the changing trends of water pressure and flow;

[0029] Temporal pattern recognition: Identify abnormal temporal patterns in the data, such as sudden pressure drops or flow fluctuations;

[0030] Dynamic adjustment of thresholds: Dynamically adjust the abnormality judgment threshold according to environmental conditions and system operation time;

[0031] Fault classification: Classify the detected anomalies into different types of faults or jams.

[0032] According to one aspect of an embodiment of the present application, the drip irrigation execution module includes:

[0033] Main water storage tank: used to store water for drip irrigation;

[0034] Intelligent control valve: installed on the water pipeline to accurately control the amount of drip irrigation water;

[0035] Drip irrigation network: distributed throughout the park to ensure even distribution of water;

[0036] Rainwater collection system: including collection hood, water collection pipe, filtering device and auxiliary water storage tank;

[0037] Among them, the water collection pipe is connected to the auxiliary water storage tank, the collection cover can be slid and adjusted to adapt to different weather conditions, and the filtering device ensures the quality of the collected rainwater.

[0038] According to one aspect of the embodiment of the present application, the rainwater collection system further includes:

[0039] Main water pump: installed in the filter device, used to extract and transport rainwater;

[0040] Auxiliary water pump: installed above the collection cover to accelerate the rainwater collection process;

[0041] Water distribution pump: installed at both ends of the filter tube to optimize water flow distribution.

[0042] According to one aspect of the embodiment of the present application, the rainwater collection system is further equipped with:

[0043] Intelligent adjustment mechanism: including hydraulic cylinder and thermal sensing device;

[0044] Retractable connecting rod: one end is connected to the hydraulic cylinder, and the other end is fixed to the collection cover;

[0045] Thermal expansion liquid: filled in the hydraulic cylinder, it can automatically adjust the position and angle of the collection hood according to changes in ambient temperature.

[0046] According to one aspect of an embodiment of the present application, an initialization step and an execution step are included;

[0047] The initialization step includes:

[0048] S1 obtains the initial value of transpiration per unit time of garden greening plants;

[0049] S2 collects initial plant image information;

[0050] The execution steps include:

[0051] S3 collects current plant image information;

[0052] S4 obtains the cumulative sunshine duration of the day;

[0053] S5 calculates a predicted transpiration value according to the initial transpiration value, the initial plant image information and the current plant image information;

[0054] S6 calculates the required drip irrigation water consumption based on the predicted transpiration value and the cumulative sunshine duration of the day;

[0055] S7 provides precise drip irrigation for landscape plants according to the calculated drip irrigation water consumption.

[0056] According to one aspect of an embodiment of the present application, the method for calculating a predicted transpiration value includes:

[0057] S51 calculates the plant coverage area in the initial plant image by using image processing technology;

[0058] S52 uses the same image processing technology to calculate the plant coverage area in the current plant image;

[0059] S53 calculates the ratio of the current plant coverage area to the initial plant coverage area;

[0060] S54 multiplies the above ratio by the initial value of transpiration to obtain a predicted value of transpiration.

[0061] According to one aspect of an embodiment of the present application, multiple image acquisition points are set up in the park to comprehensively monitor the growth status of plants.

[0062] According to one aspect of the embodiments of the present application, a drip irrigation device for maintaining garden plants and a method for using the same are provided, the method comprising:

[0063] S1. Collect historical data through the data acquisition module. The historical data includes meteorological and natural disaster data, agricultural and commercial economic indicators of agricultural products over the years, government subsidy data, etc.

[0064] S2, the data analysis module processes and analyzes the collected data, and uses deep learning models to predict agricultural and commercial economic indicators and natural disasters to obtain future changing trends.

[0065] S3, the optimization decision module generates optimized decision plans based on the data analysis results and agricultural production goals through fuzzy logic and multi-objective optimization algorithms. These plans include planting structure adjustment, cost-output ratio optimization, resource input adjustment, etc., to improve the efficiency and economic benefits of agricultural production while reducing risks.

[0066] S4, the intelligent decision support module builds a dynamic knowledge graph by integrating crop, environment, and market information, and injects the knowledge graph into the large language model for fine-tuning so that it can make reasonable suggestions.

[0067] In summary, the garden greening plant maintenance drip irrigation device and the use method thereof proposed in the present invention improve the management efficiency and decision-making accuracy of the agricultural economy through intelligent means, and provide strong support for the development of modern agriculture.

[0068] The garden greening plant maintenance drip irrigation device and the use method thereof described in the present application have the following advantages:

[0069] This application can accurately irrigate. By acquiring images of newly planted plants, identifying their types and states, and combining factors such as planting time, soil type, soil moisture, and ambient temperature and humidity, this method can accurately determine the irrigation needs of each plant, avoid excessive or insufficient watering, and achieve accurate and efficient irrigation. This application automates and intelligently utilizes technologies such as image recognition and big data analysis. This method realizes the automation and intelligence of the entire irrigation process, reduces manual labor, and improves efficiency. This application saves water and irrigates according to the actual needs of the plants, avoiding the waste of water resources caused by excessive watering, and helps save precious water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A structural diagram of a drip irrigation device for maintaining garden plants provided in one embodiment of the present application;

[0071] Figure 2 A flow chart of a drip irrigation method for maintaining landscaping plants provided in one embodiment of the present application. DETAILED DESCRIPTION

[0072] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0073] Please refer to Figure 1 , which shows a structural diagram of a garden greening plant maintenance drip irrigation device and a method of using the same provided by an embodiment of the present application;

[0074] Image acquisition module: composed of multiple cameras, used to obtain the initial and current plant image information of garden greening plants;

[0075] Environmental data acquisition module: used to obtain environmental data, including light intensity and duration;

[0076] Data storage module: used to record and store plant image information, transpiration data and environmental data;

[0077] Data processing module: responsible for plant image information analysis, transpiration calculation and drip irrigation water consumption calculation;

[0078] Control execution module: controls the operation of the drip irrigation system according to the calculation results;

[0079] Drip irrigation execution module: including water source, water pipe network and dripper, used to achieve precise drip irrigation;

[0080] Equipment detection module: Use machine learning models to monitor the working status of drip irrigation equipment in real time.

[0081] As an optional solution of this application, the device detection module includes:

[0082] Data acquisition unit: collects real-time data from pressure sensors and flow meters;

[0083] Machine learning model: A model trained based on historical data to analyze the working status of equipment;

[0084] Anomaly detection algorithms: used to identify potential equipment failures or blockages;

[0085] Predictive maintenance unit: predicts possible problems and makes maintenance recommendations based on test results;

[0086] Human-computer interaction interface: used to display test results and maintenance suggestions, and allow manual intervention.

[0087] The training process of a machine learning model includes:

[0088] Collect historical data under normal working conditions, including water pressure and flow;

[0089] Simulate different types of equipment failures and blockages and collect corresponding abnormal data;

[0090] Use the collected data to train a machine learning model, such as a support vector machine or a deep neural network;

[0091] Optimize model parameters through cross-validation to improve model accuracy and generalization ability;

[0092] Test and fine-tune the model in the actual operating environment to ensure its adaptability.

[0093] The specific machine learning model training process is:

[0094] 1. Data collection and preprocessing: Collect historical data under normal working conditions, including key parameters such as water pressure and flow. Ensure the quality and representativeness of the data, including data from different time periods, seasons, and operating conditions. Clean the data to handle missing values, outliers, and noise. Perform feature engineering to create new relevant features or transform existing features.

[0095] 2. Abnormal data generation: Simulate different types of equipment failures and blockages and collect corresponding abnormal data. Use expert knowledge and historical failure records to guide the generation of abnormal data. Consider using physical models or digital twin technology to simulate more realistic abnormal situations.

[0096] 3. Dataset division: Divide the dataset into training set, validation set and test set, usually in a ratio of 60%:20%:20%. Make sure that each set contains enough normal and abnormal samples.

[0097] 4. Model selection and training: Select an appropriate machine learning algorithm, such as support vector machine (SVM), random forest, or deep neural network. For deep learning models, design a network architecture that fits the problem. Train the model using the training set data and monitor the change in the loss function during training.

[0098] 5. Model optimization: Use the validation set for cross-validation and optimize the model's hyperparameters. For SVM, you may need to adjust the kernel function type, regularization parameters, etc. For deep neural networks, you may need to adjust the number of layers, number of neurons, learning rate, etc. Use techniques such as grid search, random search, or Bayesian optimization to automate the hyperparameter tuning process.

[0099] 6. Model evaluation: Use the test set to evaluate the performance of the model, including accuracy, precision, recall, and F1 score. Analyze the performance of the model on different types of fault detection and identify potential weaknesses.

[0100] 7. Model interpretability: Use techniques such as SHAP values ​​or LIME to explain the model’s decision-making process. Ensure that the model’s predictions are consistent with the knowledge and experience of domain experts.

[0101] 8. Deployment and fine-tuning in the actual environment: Deploy the model in the actual operating environment and conduct real-time testing. Collect actual operating data and continuously evaluate model performance. Fine-tune the model according to the actual situation, which may require the use of online learning or incremental learning techniques.

[0102] As an optional solution of the present application, the anomaly detection algorithm includes:

[0103] Real-time data preprocessing: noise reduction and standardization of collected data;

[0104] Multi-parameter joint analysis: comprehensive consideration of the changing trends of water pressure and flow;

[0105] Temporal pattern recognition: Identify abnormal temporal patterns in the data, such as sudden pressure drops or flow fluctuations;

[0106] Dynamic adjustment of thresholds: Dynamically adjust the abnormality judgment threshold according to environmental conditions and system operation time;

[0107] Fault classification: Classify the detected anomalies into different types of faults or jams.

[0108] As an optional solution of the present application, the drip irrigation execution module includes:

[0109] Main water storage tank: used to store water for drip irrigation;

[0110] Intelligent control valve: installed on the water pipeline to accurately control the amount of drip irrigation water;

[0111] Drip irrigation network: distributed throughout the park to ensure even distribution of water;

[0112] Rainwater collection system: including collection hood, water collection pipe, filtering device and auxiliary water storage tank;

[0113] Among them, the water collection pipe is connected to the auxiliary water storage tank, the collection cover can be slid and adjusted to adapt to different weather conditions, and the filtering device ensures the quality of the collected rainwater.

[0114] As an optional solution of the present application, the rainwater collection system further includes:

[0115] Main water pump: installed in the filter device, used to extract and transport rainwater;

[0116] Auxiliary water pump: installed above the collection cover to accelerate the rainwater collection process;

[0117] Water distribution pump: installed at both ends of the filter tube to optimize water flow distribution.

[0118] As an optional solution of the present application, the rainwater collection system is also equipped with:

[0119] Intelligent adjustment mechanism: including hydraulic cylinder and thermal sensing device;

[0120] Retractable connecting rod: one end is connected to the hydraulic cylinder, and the other end is fixed to the collection cover;

[0121] Thermal expansion liquid: filled in the hydraulic cylinder, it can automatically adjust the position and angle of the collection hood according to changes in ambient temperature.

[0122] A drip irrigation method for maintaining garden greening plants, characterized by comprising an initialization step and an execution step;

[0123] The initialization step includes:

[0124] S1 obtains the initial value of transpiration per unit time of garden greening plants;

[0125] S2 collects initial plant image information;

[0126] The execution steps include:

[0127] S3 collects current plant image information;

[0128] S4 obtains the cumulative sunshine duration of the day;

[0129] S5 calculates a predicted transpiration value according to the initial transpiration value, the initial plant image information and the current plant image information;

[0130] S6 calculates the required drip irrigation water consumption based on the predicted transpiration value and the cumulative sunshine duration of the day;

[0131] S7 provides precise drip irrigation for landscape plants according to the calculated drip irrigation water consumption.

[0132] As an optional solution of the present application, the method for calculating the predicted value of transpiration includes:

[0133] S51 calculates the plant coverage area in the initial plant image by using image processing technology;

[0134] S52 uses the same image processing technology to calculate the plant coverage area in the current plant image;

[0135] S53 calculates the ratio of the current plant coverage area to the initial plant coverage area;

[0136] S54 multiplies the above ratio by the initial value of transpiration to obtain a predicted value of transpiration.

[0137] As an optional solution of the present application, multiple image acquisition points are set up in the park to comprehensively monitor the growth status of plants.

Claims

1. A drip irrigation device for gardening and greening plants, characterized in that: Includes the following modules: Image acquisition module: composed of multiple cameras, used to obtain the initial and current plant image information of garden greening plants; Environmental data acquisition module: used to obtain environmental data, the environmental data including light intensity and duration; Data storage module: used to record and store plant image information, transpiration data and environmental data; Data processing module: responsible for plant image information analysis, transpiration calculation and drip irrigation water consumption calculation; Control execution module: controls the operation of the drip irrigation system according to the calculation results; Drip irrigation execution module: including water source, water pipe network and dripper, used to achieve precise drip irrigation; Equipment detection module: Use machine learning models to monitor the working status of drip irrigation equipment in real time.

2. A drip irrigation device for maintaining garden plants according to claim 1, characterized in that: The device detection module includes: Data acquisition unit: collects real-time data from pressure sensors and flow meters; Machine learning model: A model trained based on historical data to analyze the working status of equipment; Anomaly detection algorithms: used to identify potential equipment failures or blockages; Predictive maintenance unit: predicts possible problems and makes maintenance recommendations based on test results; Human-computer interaction interface: used to display test results and maintenance suggestions, and allow manual intervention.

3. A drip irrigation device for maintaining garden plants according to claim 1, characterized in that: The training process of a machine learning model includes: Collect historical data under normal working conditions, including water pressure and flow; Simulate different types of equipment failures and blockages and collect corresponding abnormal data; Use the collected data to train a machine learning model, such as a support vector machine or a deep neural network; Optimize model parameters through cross-validation to improve model accuracy and generalization ability; Test and fine-tune the model in the actual operating environment to ensure its adaptability.

4. A drip irrigation device for maintaining garden plants according to claim 1, characterized in that: The anomaly detection algorithm includes: Real-time data preprocessing: noise reduction and standardization of collected data; Multi-parameter joint analysis: comprehensive consideration of the changing trends of water pressure and flow; Temporal pattern recognition: Identify abnormal temporal patterns in the data, such as sudden pressure drops or flow fluctuations; Dynamic adjustment of thresholds: Dynamically adjust the abnormality judgment threshold according to environmental conditions and system operation time; Fault classification: Classify the detected anomalies into different types of faults or jams.

5. A drip irrigation device for maintaining garden plants according to claim 1, characterized in that: The drip irrigation execution module includes: Main water storage tank: used to store water for drip irrigation; Intelligent control valve: installed on the water pipeline to accurately control the amount of drip irrigation water; Drip irrigation network: distributed throughout the park to ensure even distribution of water; Rainwater collection system: including collection hood, water collection pipe, filtering device and auxiliary water storage tank; Among them, the water collection pipe is connected to the auxiliary water storage tank, the collection cover can be slid and adjusted to adapt to different weather conditions, and the filtering device ensures the quality of the collected rainwater.

6. A drip irrigation device for maintaining garden plants according to claim 1, characterized in that: The rainwater collection system also includes: Main water pump: installed in the filter device, used to extract and transport rainwater; Auxiliary water pump: installed above the collection cover to accelerate the rainwater collection process; Water distribution pump: installed at both ends of the filter tube to optimize water flow distribution.

7. A drip irrigation device for maintaining garden plants according to claim 1, characterized in that: The rainwater collection system is also equipped with: Intelligent adjustment mechanism: including hydraulic cylinder and thermal sensing device; Retractable connecting rod: one end is connected to the hydraulic cylinder, and the other end is fixed to the collection cover; Thermal expansion liquid: filled in the hydraulic cylinder, it can automatically adjust the position and angle of the collection hood according to changes in ambient temperature.

8. A drip irrigation method for maintaining garden plants, characterized in that: Includes initialization steps and execution steps; The initialization step includes: S1 obtains the initial value of transpiration per unit time of garden greening plants; S2 collects initial plant image information; The execution steps include: S3 collects current plant image information; S4 obtains the cumulative sunshine duration of the day; S5 calculates a predicted transpiration value according to the initial transpiration value, the initial plant image information and the current plant image information; S6 calculates the required drip irrigation water consumption based on the predicted transpiration value and the cumulative sunshine duration of the day; S7 provides precise drip irrigation for landscape plants according to the calculated drip irrigation water consumption.

9. The drip irrigation method for maintaining garden plants according to claim 8, characterized in that: The method for calculating the predicted value of transpiration comprises: S51 calculates the plant coverage area in the initial plant image by using image processing technology; S52 uses the same image processing technology to calculate the plant coverage area in the current plant image; S53 calculates the ratio of the current plant coverage area to the initial plant coverage area; S54 multiplies the above ratio by the initial value of transpiration to obtain a predicted value of transpiration.

10. The drip irrigation method for maintaining garden plants according to claim 8, characterized in that: Multiple image collection points are set up in the park to comprehensively monitor the growth conditions of plants.

Citation Information

Cited By

  • Distributed forestry seedling raising spraying mechanism intelligent management and control system

    CN121176348A

  • Distributed forestry seedling raising spraying mechanism intelligent management and control system

    CN121176348B