Intelligent Environment Monitoring System and Method for Underforest Planting

Abstract

The present invention provides an intelligent environmental monitoring system and method for under-forest planting. Among them, the system includes: a sensor deployment subsystem for deploying a sensor cluster; an under-forest monitoring data acquisition subsystem for acquiring under-forest monitoring data through the sensor cluster; an intelligent sprinkler control subsystem for performing intelligent sprinkler irrigation based on deep learning technology according to the under-forest monitoring data; and an intelligent early warning subsystem for performing intelligent environmental early warning based on fuzzy control technology according to the under-forest monitoring data. The intelligent environmental monitoring system and method for under-forest planting of the present invention constructs an intelligent sprinkler irrigation model based on deep learning, which can determine the on-off time of the sprinkler irrigation system according to meteorological conditions, current soil and air humidity, so as to achieve the soil and air humidity suitable for the growth of under-forest plants, and the sprinkler irrigation control process is more intelligent; constructs an intelligent environmental early warning model, which helps to remind users of the growth status of plants and improve the production efficiency and product quality of under-forest plants.

Description

Technical Field

[0001] The present invention relates to the technical field of smart agriculture, and particularly to an intelligent environment monitoring system and method for under-forest planting. Background Art

[0002] Smart agriculture is a new agricultural model that applies modern information technology to agricultural production. By integrating technologies such as sensors, the Internet of Things, big data analysis, and artificial intelligence, it realizes precise monitoring and management of the agricultural production process, thereby improving agricultural production efficiency, reducing costs, enhancing product quality, and achieving sustainable development.

[0003] Currently, the level of intelligence (intelligent control) in under-forest planting needs to be improved. For example, how to effectively and accurately identify the production environment conditions of planted products (such as Ganoderma lucidum), how to determine the sprinkler irrigation time and duration, etc. These problems still need to be solved, which to a certain extent restricts production efficiency and product quality.

[0004] In view of this, there is an urgent need for an intelligent environment monitoring system and method for under-forest planting to at least solve the above deficiencies. Summary of the Invention

[0005] One of the purposes of the present invention is to provide an intelligent environment monitoring system and method for under-forest planting, which constructs an intelligent sprinkler irrigation model based on deep learning. It can determine the on-off time of the sprinkler irrigation system according to meteorological conditions, current soil and air humidity, so as to achieve the soil and air humidity suitable for the growth of under-forest plants, and the sprinkler irrigation control process is more intelligent; it constructs an intelligent environment warning model, which helps to remind users of the growth status of planted plants, and improves the production efficiency and product quality of under-forest planted plants.

[0006] The intelligent environment monitoring system for under-forest planting provided by the embodiment of the present invention includes:

[0007] A sensor layout subsystem for laying out a sensor cluster;

[0008] An under-forest monitoring data acquisition subsystem for performing intelligent environment monitoring of under-forest planting through the sensor cluster and acquiring under-forest monitoring data;

[0009] An intelligent sprinkler irrigation control subsystem for performing intelligent sprinkler irrigation based on deep learning technology according to the under-forest monitoring data;

[0010] An intelligent warning subsystem for performing intelligent environment warning based on fuzzy control technology according to the under-forest monitoring data.

[0011] Preferably, the sensor layout subsystem includes:

[0012] A layout position determination module for determining the upwind position on the site of the target planting base for under-forest planting;

[0013] A deployment module for deploying a sensor cluster at the upwind position of the site; wherein, the deployed sensor cluster includes: a light sensor, an air temperature and humidity sensor, a carbon dioxide sensor, a soil temperature sensor, and a soil humidity sensor.

[0014] Preferably, the under-forest monitoring data acquisition subsystem includes:

[0015] An under-forest monitoring data acquisition module for acquiring under-forest monitoring data through the sensor cluster based on a preset monitoring period and a cloud server.

[0016] Preferably, the intelligent sprinkler irrigation control subsystem includes:

[0017] An intelligent irrigation model construction module for constructing an intelligent irrigation model based on deep learning technology;

[0018] A sprinkler irrigation control module for performing intelligent sprinkler irrigation based on the intelligent irrigation model and according to the under-forest monitoring data.

[0019] Among them, the intelligent irrigation model construction module includes:

[0020] A first training sub-module for collecting historical monitored environmental indicators during the non-irrigation period, capturing the temporal changes of the historical monitored environment during the non-irrigation period, and training an irrigation start model;

[0021] A second training sub-module for collecting historical monitored environmental indicators during the irrigation period, capturing the temporal changes of the historical monitored environment during the irrigation period, and training an irrigation stop model;

[0022] An integration module for obtaining an intelligent irrigation model according to the irrigation start model and the irrigation stop model;

[0023] Among them, the sprinkler irrigation control module includes:

[0024] An irrigation start time determination sub-module for, when irrigation is not started, performing multi-time step prediction output using an LSTM model, and when the predicted air relative humidity reaches a preset first rule condition, counting the first time step length to determine the irrigation start time;

[0025] An irrigation stop time determination sub-module for, when irrigation is started, performing multi-time step prediction output using an LSTM model, and when the predicted air relative humidity reaches a preset second rule condition, counting the second time step length to determine the irrigation stop time.

[0026] Preferably, the intelligent irrigation model construction module also performs the following operations:

[0027] Obtain the first artificial cultivation record of the target planting base;

[0028] Extract the first artificial cultivation feature based on a preset cultivation feature extraction template; the first artificial cultivation feature includes: the first irrigation timing, the first irrigation parameter, and the first irrigation effect;

[0029] Screen the first artificial cultivation records where the first irrigation effect is greater than or equal to a preset irrigation effect threshold, and use them as the first target artificial cultivation records;

[0030] Connect to the big data supplement node to obtain the second artificial cultivation records of the same species as the understory plants;

[0031] Extract the second artificial cultivation feature based on the cultivation feature extraction template; the second artificial cultivation feature includes: the second irrigation timing, the second irrigation parameter, and the second irrigation effect;

[0032] Screen the second artificial cultivation records where the second irrigation effect is greater than or equal to a preset irrigation effect threshold, and use them as the second target artificial cultivation records;

[0033] Conduct a first suitability analysis on the irrigation environment of the second irrigation timing, and determine whether the first suitability analysis passes;

[0034] Conduct a second suitability analysis on the second irrigation parameter, and determine whether the second suitability analysis passes;

[0035] If both the first suitability analysis and the second suitability analysis pass, use the corresponding second target artificial cultivation record as the third target artificial cultivation record;

[0036] Based on deep learning technology, train an intelligent irrigation model according to the first target artificial cultivation record and the third target artificial cultivation record;

[0037] Among them, conducting a second suitability analysis on the second irrigation parameter and determining whether the second suitability analysis passes includes:

[0038] Judge whether the second irrigation parameter can be achieved according to the irrigation capacity of the irrigation device;

[0039] If it can be achieved, the second suitability analysis passes.

[0040] Preferably, conducting a first suitability analysis on the irrigation environment of the second irrigation timing and determining whether the first suitability analysis passes includes:

[0041] Obtain the first environmental characteristic data of the first irrigation timing, and determine the environmental characteristic data intervals of different first environmental characteristic types according to the first environmental characteristic data;

[0042] Obtain the second environmental characteristic data of the second irrigation timing;

[0043] Determine the matching interval of the second environmental characteristic data in the environmental characteristic data interval according to the second environmental characteristic type of the second environmental characteristic data;

[0044] Judge whether the second environmental characteristic data falls within the matching interval. If so, obtain the first target weight of the first environmental characteristic type corresponding to the matching interval;

[0045] If not, obtain the second target weight of the first environmental characteristic type corresponding to the matching interval;

[0046] Obtain the data distribution of the matching interval;

[0047] Based on the percentile method and according to the data distribution, determine the benchmark interval value of the matching interval;

[0048] Determine the difference value between the second environmental characteristic data and the benchmark interval value, and calculate the absolute value of the difference between the difference value and the length of the matching interval;

[0049] According to the quotient value of the absolute value and the length of the matching interval, lower the second target weight;

[0050] Determine the environmental characteristic recurrence degree according to the sum value of the first target weight corresponding to the second environmental characteristic type and / or the lowered second target weight;

[0051] If the environmental characteristic recurrence degree is greater than or equal to the preset environmental characteristic recurrence degree threshold, the analysis of the first suitability analysis passes.

[0052] Preferably, the intelligent early warning subsystem includes:

[0053] The membership function design module is used to design the membership function based on the growth environment requirements of the understory planting target;

[0054] The fuzzy quantization result determination module is used to perform fuzzy quantization on the understory monitoring data according to the membership function to determine the fuzzy quantization result;

[0055] The knowledge rule base construction module is used to construct the knowledge rule base based on expert experience and planting experience;

[0056] The fuzzy reasoning module is used to perform fuzzy reasoning according to the fuzzy quantization result and the knowledge rule base to obtain the fuzzy output quantity;

[0057] The fuzzy early warning module is used to perform fuzzy decision-making according to the fuzzy output quantity for fuzzy early warning.

[0058] The intelligent environmental monitoring method for understory planting provided by the embodiment of the present invention includes:

[0059] Step 1: Arrange the sensor cluster;

[0060] Step 2: Through the sensor cluster, conduct intelligent environmental monitoring for underforest planting to obtain underforest monitoring data;

[0061] Step 3: Based on deep learning technology, conduct intelligent sprinkler irrigation according to the underforest monitoring data;

[0062] Step 4: Based on fuzzy control technology, conduct intelligent environmental early warning according to the underforest monitoring data.

[0063] Preferably, Step 1: Deploy the sensor cluster, including:

[0064] Determine the upwind position of the site of the target planting base for underforest planting;

[0065] Deploy the sensor cluster at the upwind position of the site; among them, deploying the sensor cluster includes: a light sensor, an air temperature and humidity sensor, a carbon dioxide sensor, a soil temperature sensor, and a soil humidity sensor.

[0066] Preferably, Step 2: Through the sensor cluster, conduct intelligent environmental monitoring for underforest planting to obtain underforest monitoring data, including:

[0067] Based on a preset monitoring period and the cloud server, obtain underforest monitoring data through the sensor cluster.

[0068] Preferably, Step 3: Based on deep learning technology, conduct intelligent sprinkler irrigation according to the underforest monitoring data, including:

[0069] Based on deep learning technology, construct an intelligent irrigation model;

[0070] Based on the intelligent irrigation model, conduct intelligent sprinkler irrigation according to the underforest monitoring data;

[0071] Among them, based on deep learning technology, constructing the intelligent irrigation model includes:

[0072] Collect historical monitoring environmental indicators during the non-irrigation period, capture the temporal changes of the historical monitoring environment during the non-irrigation period, and train the irrigation start model;

[0073] Collect historical monitoring environmental indicators during the irrigation period, capture the temporal changes of the historical monitoring environment during the irrigation period, and train the irrigation stop model;

[0074] According to the irrigation start model and the irrigation stop model, obtain the intelligent irrigation model;

[0075] Among them, based on the intelligent irrigation model, conducting intelligent sprinkler irrigation according to the underforest monitoring data includes:

[0076] When irrigation is not turned on, use the LSTM model to perform multi-step prediction output. When the predicted relative air humidity reaches the preset first rule condition, count the length of the first time step and determine the irrigation start time;

[0077] When irrigation is turned on, use the LSTM model to perform multi-step prediction output. When the predicted relative air humidity reaches the preset second rule condition, count the length of the second time step and determine the irrigation stop time.

[0078] Preferably, step 4: Based on fuzzy control technology, perform environmental intelligent warning according to the under-forest monitoring data, including:

[0079] Design a membership function based on the growth environment requirements of the under-forest planting target;

[0080] According to the membership function, perform fuzzy quantification on the under-forest monitoring data to determine the fuzzy quantification result;

[0081] Build a knowledge rule base based on expert experience and planting experience;

[0082] Perform fuzzy reasoning according to the fuzzy quantification result and the knowledge rule base to obtain a fuzzy output quantity;

[0083] Perform fuzzy decision-making according to the fuzzy output quantity to conduct fuzzy warning.

[0084] The beneficial effects of the present invention are as follows:

[0085] The present invention constructs an intelligent sprinkler irrigation model based on deep learning, which can determine the opening and closing time of the sprinkler irrigation system according to meteorological conditions, current soil and air humidity, so as to achieve the soil and air humidity suitable for the growth of under-forest plants, and the sprinkler irrigation control process is more intelligent; construct an intelligent environment warning model, which helps to remind users of the growth status of plants and improve the production efficiency and product quality of under-forest plants.

[0086] The technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Description of the Drawings

[0087] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the accompanying drawings:

[0088] Figure 1 is a schematic diagram of the intelligent environment monitoring system for under-forest planting in the embodiment of the present invention;

[0089] Figure 2 is the schematic diagram of the fuzzy control principle of the intelligent environment monitoring system for under-forest planting in the embodiment of the present invention;

[0090] Figure 3This is the viewing applet interface of the intelligent environment monitoring system for under-forest planting in the embodiments of the present invention;

[0091] Figure 4 This is the design diagram of the automatic monitoring and remote control system for intelligent environment of under-forest planting in the embodiments of the present invention;

[0092] Figure 5 This is the schematic diagram of the intelligent environment monitoring method for under-forest planting in the embodiments of the present invention. Detailed implementation manners

[0093] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for the purpose of illustrating and explaining the present invention, and are not intended to limit the present invention.

[0094] The embodiments of the present invention provide an intelligent environment monitoring system for under-forest planting, as Figure 1 shown, including:

[0095] A sensor layout subsystem 1 for laying out a sensor cluster; wherein, the sensor cluster is: sensors laid in the under-forest planting area for collecting environmental data of the layout area;

[0096] An under-forest monitoring data acquisition subsystem 2 for monitoring the intelligent environment of under-forest planting through the sensor cluster and acquiring under-forest monitoring data; wherein, the under-forest monitoring data is: light data, air temperature and humidity data, carbon dioxide concentration data, soil temperature data, and soil humidity data;

[0097] An intelligent sprinkler control subsystem 3 for performing intelligent sprinkler irrigation based on deep learning technology according to the under-forest monitoring data; wherein, performing intelligent sprinkler irrigation based on deep learning technology according to the under-forest monitoring data means: deeply learning a large amount of sprinkler irrigation data of under-forest plants (such as: Ganoderma lucidum), automatically adjusting the operation of the sprinkler irrigation system according to the collected under-forest monitoring data, and realizing precise irrigation;

[0098] An intelligent early warning subsystem 4 for performing environmental intelligent early warning based on fuzzy control technology according to the under-forest monitoring data. Among them, based on the fuzzy control principle, aiming at the growth environment requirements of under-forest plants for light intensity, temperature and humidity in different growth periods, based on appropriate environmental thresholds, combined with the characteristics of growth periods, different membership functions are designed, including Gaussian membership function, trapezoidal membership function, and triangular membership function, and a knowledge base and a rule base are established, so as to adopt different early warning times for the environmental indicators in the growth period. The fuzzy control principle is as Figure 2 shown.

[0099] The working principle and beneficial effects of the above technical solutions are:

[0100] The construction of the automatic monitoring and remote intelligent monitoring system for the underforest planting environment includes two parts of work content:

[0101] 1) Layout of the automatic monitoring and remote control system for the underforest planting environment and sprinkler irrigation;

[0102] 2) Development of the intelligent monitoring system for the underforest planting environment based on deep learning and fuzzy control.

[0103] 1) Layout of the automatic monitoring and remote control system for the underforest planting environment and sprinkler irrigation

[0104] 1.1) Layout of the automatic atomizing sprinkler irrigation system

[0105] Based on high-pressure atomizing sprinkler irrigation equipment, filters and control boxes as the hardware foundation, build a full-coverage atomizing sprinkler irrigation system. For example: according to the planting interval width of Ganoderma lucidum, layout the interval width of water mist nozzles (1.2m), and according to the humidity requirement range of Ganoderma lucidum, layout the height of water mist nozzles. After the water source is filtered and pressurized, high-pressure atomizing sprinkler irrigation is realized to ensure the high humidity requirement of the planting environment; combined with intelligent valves, GPRS mobile communication technology, cloud servers and remote control technology, the data information is transmitted back to the cloud data center through the intelligent gateway. Managers can remotely view and control the on-site sprinkler irrigation facilities through the WEB terminal or mobile APP. The system supports preset time and operation cycle, and after reaching the preset conditions, the system will automatically operate the on-site equipment to complete the control action.

[0106] 1.2) Layout of the automatic monitoring station based on the intelligent environment

[0107] Real-time monitor the environmental information such as the atmospheric environment information and soil environment information of the underforest planting through the sensor cluster and the automatic weather station. Layout the environmental automatic monitoring station at the upwind position of the planting base site. The monitoring station consists of sensors for light, air temperature and humidity, carbon dioxide, soil temperature and soil humidity. The monitoring station transmits the environmental information data to the underforest intelligent monitoring system server through the 5G network and the cloud server every 1 minute.

[0108] 2) Development of the intelligent monitoring system for the underforest planting environment based on deep learning and fuzzy control

[0109] 2.1) Intelligent sprinkler irrigation control model based on LSTM

[0110] Apply artificial intelligence and deep learning algorithms to establish the response relationship between soil humidity, air humidity and sprinkler irrigation time duration / pressure under different meteorological conditions (light, temperature, carbon dioxide, etc.), and construct an intelligent sprinkler irrigation prediction model. The intelligent sprinkler irrigation prediction model can determine the on / off time of the sprinkler irrigation system according to the meteorological conditions and the current soil and air humidity to achieve the appropriate soil and air humidity for underforest planting.

[0111] The intelligent irrigation model is divided into two parts, including the irrigation start and irrigation stop models. The irrigation start model collects the monitored environmental indicators of the understory plant planting base during the non-irrigation period and captures the temporal changes in the growth environment of the understory plants during the non-irrigation period. The irrigation stop model collects the monitored environmental indicators of the understory plant planting base during the irrigation period and captures the temporal changes in the growth environment of the understory plants during the irrigation period.

[0112] Taking the prediction of the main control index, relative air humidity, as an example, considering that the current relative air humidity is affected by relevant indicators within a certain time series, the intelligent irrigation model uses the widely used LSTM time series model to predict the relative air humidity of the understory plants.

[0113] The basic computational unit of the LSTM model is as follows:

[0114] I t = σ(X t W xi + H t-1 W hi + b i )

[0115] F t = σ(X t W xf + H t-1 W hf + b f )

[0116] O t = σ(X t W xo + H t-1 W ho + b o )

[0117]

[0118] H t = O t ⊙ tanh(C t )

[0119] Y = H t ⊙ W xy + b y

[0120] Among them, I t , F t , O t are the input gate, forget gate, and output gate features at time t in sequence. C t are the candidate memory cell and memory cell at time t respectively. W xi , W hi , W xf , Whf , W xo , W ho , W xc , W hc , W xy , b i , b f , b o , b c , b y are model parameters, and X t is the input data feature, which is the monitoring environment index feature at time t in the time series here. H t-1 , H t are hidden states. Y is the predicted index, which is the relative humidity of the air at time t + 1 here, and is obtained by learning and predicting the features within the time series.

[0121] Based on the LSTM regression model, the relative humidity of the air at multiple time steps can be predicted. When irrigation is not turned on, the LSTM regression model is used for multi-time-step prediction output. When the predicted relative humidity of the air reaches the preset rule condition (unsuitable growth environment), the time step length at this time is counted, and the irrigation time can be obtained. Similarly, during the irrigation period, the LSTM regression model is used for multi-time-step prediction output. When the predicted relative humidity of the air reaches the preset rule condition (suitable growth condition), the time step length at this time is counted, and the irrigation off time can be obtained.

[0122] 2.2) Environment intelligent early warning model based on fuzzy control algorithm

[0123] Combining expert experience and field planting experience, clarify the ranges of light intensity, temperature and humidity suitable for different growth periods of underforest plants. Apply the fuzzy decision-making algorithm to construct an intelligent environment early warning model. For the scenarios where environmental elements exceed the suitable range, conduct intelligent early warning and forecasting to remind the administrator to take corresponding measures.

[0124] Based on the fuzzy control principle, aiming at the growth environment requirements of underforest plants for light intensity, temperature and humidity at different growth periods, based on the appropriate environmental thresholds and combined with the characteristics of growth periods, design different membership functions, including Gaussian membership function, trapezoidal membership function and triangular membership function, establish a knowledge base and a rule base, so as to adopt different early warning times for the environmental indicators during the growth period, thereby reducing the false alarm rate and interference frequency.

[0125] 2.3) Integrated intelligent control system for underforest planting environment

[0126] The intelligent monitoring and sprinkler irrigation system for underforest planting is implemented in the form of an SQL database + model + mini-program, which is convenient for users to log in and access anytime and anywhere. Through the mini-program, the on-site planting environment can be remotely viewed. The mini-program interface is as shown in Figure 3As shown in the figure, remote manual control of sprinkler irrigation is carried out. At the same time, based on the intelligent control model of the planting environment and the early warning model algorithm, the system realizes the real-time automatic control of the sprinkler irrigation system and the early warning of the risk of exceeding the standard of growth environment parameters. The design diagram of the intelligent environment automatic monitoring and sprinkler irrigation remote control system for underforest planting is as Figure 4 shown.

[0127] The system background database is built using mainstream SQL data to store the monitoring indicators of the underforest planting environment in real time. To avoid the loss of monitoring data, the system determines abnormal data in real time and sends a data anomaly alert to the administrator. The judgment logic is as follows: ① continuous missing for 1 hour; or ② more than 20% of the data is missing within a day, that is, the number of missing minutes accounts for more than 20% of the total minutes of the whole day; or ③ the soil humidity, air humidity, and carbon dioxide among them have continuous 0 values for 1 hour; or ④ more than 20% of the data of the soil humidity, air humidity, and carbon dioxide among them is 0 within a day.

[0128] The system includes five modules. From top to bottom, they are Module 1: Display the switch status of the sprinkler irrigation equipment and the key monitoring indicator (soil humidity); Module 2: Display the real-time values of the monitoring indicators; Module 3: Display the time-series values of the monitoring indicators, and the time and indicators can be selected through the screening button; Module 4: Display the current working conditions of the sprinkler irrigation equipment; Module 5: Click the "Start Equipment" button to perform remote irrigation operations. Click the "Abnormal Data" button to view the abnormal data judged by the system.

[0129] The present invention constructs an intelligent sprinkler irrigation model based on deep learning, which can determine the switch time of the sprinkler irrigation system according to meteorological conditions, current soil and air humidity, so as to achieve the soil and air humidity suitable for the growth of underforest plants, and the sprinkler irrigation control process is more intelligent; constructs an intelligent environment early warning model, which helps to remind users of the growth status of plants and improve the production efficiency and product quality of underforest plants.

[0130] In one embodiment, the sensor layout subsystem includes:

[0131] A layout position determination module for determining the on-wind direction position of the site of the target planting base for underforest planting; wherein, the target planting base is: the planting base corresponding to the underforest plants;

[0132] A layout module for laying out a sensor cluster at the on-wind direction position of the site; wherein, laying out the sensor cluster includes: a light sensor, an air temperature and humidity sensor, a carbon dioxide sensor, a soil temperature sensor, and a soil humidity sensor.

[0133] The working principle and beneficial effects of the above technical solution are:

[0134] The present invention monitors environmental information such as atmospheric environment information and soil environment information of under-forest planting in real time through a sensor cluster and an automatic weather station. An environmental automatic monitoring station is arranged at the upwind position of the planting base site, improving the rationality of the sensor position layout.

[0135] In one embodiment, the under-forest monitoring data acquisition subsystem includes:

[0136] The under-forest monitoring data acquisition module is used to obtain under-forest monitoring data through the sensor cluster based on a preset monitoring period and the cloud server. Among them, the preset monitoring period is set manually, for example: 1 minute.

[0137] The working principle and beneficial effects of the above technical solution are:

[0138] In the present invention, the monitoring station transmits environmental information data to the under-forest intelligent monitoring system server through the 5G network and the cloud server every 1 minute, making data monitoring more timely.

[0139] In one embodiment, the intelligent sprinkler irrigation control subsystem includes:

[0140] The intelligent irrigation model construction module is used to construct an intelligent irrigation model based on deep learning technology;

[0141] The sprinkler irrigation control module is used to perform intelligent sprinkler irrigation based on the intelligent irrigation model and according to the under-forest monitoring data.

[0142] Among them, the intelligent irrigation model construction module includes:

[0143] The first training sub-module is used to collect historical monitoring environmental indicators during the non-irrigation period, capture the temporal changes of the historical monitoring environment during the non-irrigation period, and train the irrigation start model;

[0144] The second training sub-module is used to collect historical monitoring environmental indicators during the irrigation period, capture the temporal changes of the historical monitoring environment during the irrigation period, and train the irrigation stop model;

[0145] The integration module is used to obtain the intelligent irrigation model according to the irrigation start model and the irrigation stop model;

[0146] Among them, the sprinkler irrigation control module includes:

[0147] The irrigation start time determination sub-module is used to, when irrigation is not started, perform multi-time step prediction output using the LSTM model. When the predicted air relative humidity reaches a preset first rule condition, count the first time step length and determine the irrigation start time; among them, the first rule condition is: an environment unsuitable for the growth of under-forest plants; the first time step length is: the time step length from the current moment to the predicted irrigation start time;

[0148] The irrigation shutdown time determination sub-module is used to, when irrigation is turned on, perform multi-time-step prediction output using the LSTM model. When the predicted relative air humidity reaches the preset second rule condition, the second time-step length is statistically calculated to determine the irrigation shutdown time. Here, the second rule condition is: the growth conditions suitable for the understory plants; the second time-step length is: the time step length from the current moment to the predicted irrigation shutdown time.

[0149] The working principle and beneficial effects of the above technical solution are as follows:

[0150] The present invention applies artificial intelligence and deep learning algorithms to establish the response relationship between soil humidity, air humidity and the duration / pressure of sprinkler irrigation under different meteorological conditions (such as light, temperature, carbon dioxide, etc.), and constructs an intelligent sprinkler irrigation prediction model. The intelligent sprinkler irrigation prediction model can determine the on / off time of the sprinkler irrigation system according to the meteorological conditions and the current soil and air humidity, so as to achieve the soil and air humidity suitable for understory planting;

[0151] The intelligent irrigation model is divided into two parts, including an irrigation start model and an irrigation shutdown model; the irrigation start model collects the monitored environmental indicators of the target planting base during the non-irrigation period and captures the temporal changes in the growth environment of the understory plants during the non-irrigation period. The irrigation shutdown model collects the monitored environmental indicators of the target planting base during the irrigation period and captures the temporal changes in the growth environment of the understory plants during the irrigation period;

[0152] Taking the prediction of the main control index, relative air humidity, as an example, considering that the current relative air humidity is affected by relevant indicators within a certain time series, the intelligent irrigation model uses the widely used LSTM time series model at present to predict the relative air humidity of the understory plants;

[0153] Based on the LSTM regression model, the relative air humidity of multiple time steps can be predicted; when irrigation is not turned on, the LSTM regression model is used for multi-time-step prediction output. When the predicted relative air humidity reaches the preset rule condition (unsuitable growth environment), the time step length at this time is statistically calculated to obtain the irrigation time; similarly, during the irrigation period, the LSTM regression model is used for multi-time-step prediction output. When the predicted relative air humidity reaches the preset rule condition (suitable growth conditions), the time step length at this time is statistically calculated to obtain the irrigation shutdown time.

[0154] In one embodiment, the intelligent irrigation model construction module further performs the following operations:

[0155] Obtain the first artificial cultivation record of the target planting base; where the first artificial cultivation record is: the record of artificially cultivating understory plants in the target planting base in history, such as: watering record;

[0156] Extract the first artificial cultivation feature based on a preset cultivation feature extraction template; the first artificial cultivation feature includes: the first irrigation timing, the first irrigation parameter, and the first irrigation effect; among them, the preset cultivation feature extraction template is: a template for artificial cultivation records to extract artificial cultivation features by comparison; the irrigation timing is: the environmental parameters at the time of irrigation; the irrigation parameter is: the amount of water poured; the irrigation effect is: the comparison score of the growth state and the average growth state of the understory plants between the time after watering and the next watering time.

[0157] Screen the first artificial cultivation records with the first irrigation effect greater than or equal to a preset irrigation effect threshold, and use them as the first target artificial cultivation records; among them, the preset irrigation effect threshold is set manually in advance.

[0158] Connect to the big data supplement node to obtain the second artificial cultivation records of the same species as the understory plants; among them, the big data supplement node is: an understory plant cultivation communication platform.

[0159] Extract the second artificial cultivation feature based on the cultivation feature extraction template; the second artificial cultivation feature includes: the second irrigation timing, the second irrigation parameter, and the second irrigation effect.

[0160] Screen the second artificial cultivation records with the second irrigation effect greater than or equal to a preset irrigation effect threshold, and use them as the second target artificial cultivation records.

[0161] Conduct a first suitability analysis on the irrigation environment of the second irrigation timing, and determine whether the first suitability analysis passes; among them, the first suitability analysis is: determining whether the second irrigation timing is suitable for local application.

[0162] Conduct a second suitability analysis on the second irrigation parameter, and determine whether the second suitability analysis passes; among them, the second suitability analysis is: determining whether the second irrigation parameter is suitable for local application.

[0163] If both the first suitability analysis and the second suitability analysis pass, use the corresponding second target artificial cultivation records as the third target artificial cultivation records.

[0164] Based on deep learning technology, train an intelligent irrigation model according to the first target artificial cultivation records and the third target artificial cultivation records.

[0165] Among them, conducting a second suitability analysis on the second irrigation parameter and determining whether the second suitability analysis passes includes:

[0166] According to the irrigation capacity of the irrigation device, determine whether the second irrigation parameter can be achieved; among them, the irrigation device is the irrigation device used in the target planting base; when determining whether the second irrigation parameter can be achieved, determine whether the second irrigation parameter can be achieved based on the irrigation capacity.

[0167] If it can be achieved, the second suitability analysis passes.

[0168] The working principle and beneficial effects of the above technical solution are as follows:

[0169] The present invention introduces two types of artificially cultivated records for subsequent training of the intelligent irrigation model; the first is the first artificially cultivated record of the target planting base. Since the first artificially cultivated record is directly obtained from this base, it is more applicable; a cultivation feature extraction template is introduced to determine the first irrigation timing, the first irrigation parameters, and the first irrigation effect, and the first target artificially cultivated records with the first irrigation effect greater than or equal to the preset irrigation effect threshold are screened; the second is to connect to the big data supplementary node to obtain the second artificially cultivated record of the same type as the understory plants, and based on the cultivation feature extraction template, extract the second irrigation timing, the second irrigation parameters, and the second irrigation effect, and determine the second target artificially cultivated records with the second irrigation effect greater than or equal to the preset irrigation effect threshold; considering that the irrigation mechanism and growth environment of the understory plants corresponding to the second artificially cultivated record obtained from big data may be quite different from those of the target planting base, a first suitability analysis is performed on the second irrigation timing and a second suitability analysis is performed on the second irrigation parameters to screen the third target artificially cultivated records suitable for use in local irrigation model training; based on deep learning technology, an intelligent irrigation model is trained according to the first target artificially cultivated records and the third target artificially cultivated records, improving the comprehensiveness and rationality of the irrigation model training.

[0170] In one embodiment, a first suitability analysis is performed on the irrigation environment of the second irrigation timing, and it is judged whether the first suitability analysis passes, including:

[0171] Obtain the first environmental characteristic data of the first irrigation timing, and according to the first environmental characteristic data, determine the environmental characteristic data intervals of different first environmental characteristic types; wherein, the first environmental characteristic data is the environmental data corresponding to the first irrigation timing, such as: light intensity, air temperature and humidity, carbon dioxide content, and soil temperature and humidity; the environmental characteristic data intervals of different first environmental characteristic types are: the value ranges of the first environmental characteristic data of the first environmental characteristic type determined by summarizing the first environmental characteristic data of the same first environmental characteristic type, such as: taking the minimum value obtained by summarization as the interval minimum value and taking the maximum value obtained by summarization as the interval maximum value;

[0172] Obtain the second environmental characteristic data of the second irrigation timing; wherein, the second environmental characteristic data is the environmental data corresponding to the second irrigation timing;

[0173] Determine the matching interval of the second environmental characteristic data in the environmental characteristic data interval according to the second environmental characteristic type of the second environmental characteristic data; wherein, the first environmental characteristic type corresponding to the matching interval is consistent with the second environmental characteristic type of the second environmental characteristic data corresponding to the matching interval;

[0174] Judge whether the second environmental characteristic data falls within the matching interval. If so, obtain the first target weight of the first environmental characteristic type corresponding to the matching interval; wherein, the first target weight of the first environmental characteristic type is preset manually;

[0175] If not, obtain the second target weight of the first environmental characteristic type corresponding to the matching interval;

[0176] Obtain the data distribution of the matching interval; wherein, the data distribution is: which first environmental characteristic data is at which interval position in the matching interval;

[0177] Based on the percentile method and according to the data distribution, determine the reference interval value of the matching interval; wherein, based on the percentile method and according to the data distribution, the reference interval value of the matching interval is: determine the upper and lower bounds of the matching interval according to specific percentiles (such as: 2.5% and 97.5%), obtain the reference interval containing 95% of the reference individuals, and calculate the average value of the first environmental characteristic data within the reference interval to obtain the reference interval value;

[0178] Determine the difference value between the second environmental characteristic data and the reference interval value, and calculate the absolute value of the difference between the difference value and the length of the matching interval;

[0179] According to the quotient value of the absolute value and the length of the matching interval, down-regulate the second target weight; wherein, when down-regulating the second target weight, the quotient value and the second target weight are multiplied correspondingly;

[0180] Calculate the sum value of the first target weight corresponding to the second environmental characteristic type and / or the down-regulated second target weight, and determine the environmental characteristic recurrence degree;

[0181] If the environmental characteristic recurrence degree is greater than or equal to the preset environmental characteristic recurrence degree threshold, the analysis of the first suitability analysis passes. Wherein, the preset environmental characteristic recurrence degree threshold is preset manually.

[0182] The working principle and beneficial effects of the above technical solution are:

[0183] The present invention obtains the first environmental characteristic data at the first irrigation time, conducts data statistics, and determines the environmental characteristic data interval corresponding to each first environmental characteristic type; determines the second environmental characteristic type of the second environmental characteristic data, and determines the matching interval corresponding to the environmental characteristic data interval of the second environmental characteristic type; determines whether the second environmental characteristic data falls within the matching interval. If the second environmental characteristic data falls within the matching interval, it indicates that the environmental data reuse degree of the first environmental characteristic type corresponding to the matching interval is high, and determines the first target weight of the corresponding first environmental characteristic type; if the second environmental characteristic data does not fall within the matching interval, obtains the second target weight of the first environmental characteristic type corresponding to the matching interval, introduces the percentile method, and determines the reference interval value according to the data distribution of the matching interval; calculates the downward adjustment weight (the quotient of the absolute value and the length of the matching interval) of the second target weight according to the difference value between the second environmental characteristic data and the reference interval value, and downward adjusts the second target weight; takes the sum value of the first target weight corresponding to the second environmental characteristic type and / or the downward adjusted second target weight as the environmental characteristic recurrence degree. When the environmental characteristic recurrence degree is greater than or equal to the preset environmental characteristic recurrence degree threshold, it is determined that the analysis of the first suitability analysis passes, improving the accuracy of the analysis process of the first suitability analysis.

[0184] In one embodiment, the intelligent early warning subsystem includes:

[0185] A membership function design module for designing a membership function based on the growth environment requirements of the underforest planting target;

[0186] A fuzzy quantization result determination module for performing fuzzy quantization on the underforest monitoring data according to the membership function to determine the fuzzy quantization result;

[0187] A knowledge rule base construction module for constructing a knowledge rule base based on expert experience and planting experience;

[0188] A fuzzy inference module for performing fuzzy inference according to the fuzzy quantization result and the knowledge rule base to obtain a fuzzy output quantity;

[0189] A fuzzy early warning module for performing fuzzy decision-making according to the fuzzy output quantity to conduct fuzzy early warning.

[0190] The working principle and beneficial effects of the above technical solution are as follows:

[0191] The present invention combines expert experience and field planting experience to clarify the ranges of light intensity, temperature and humidity suitable for different growth periods of underforest plants; applies the fuzzy decision-making algorithm to construct an intelligent environment early warning model; conducts intelligent early warning and forecasting for scenarios where environmental elements exceed the suitable range, and reminds the administrator to take corresponding measures;

[0192] Based on the fuzzy control principle, aiming at the growth environment requirements of under-forest plants for light intensity, temperature and humidity in different growth periods, based on appropriate environmental thresholds, combined with the characteristics of growth periods, different membership functions are designed, including Gaussian membership function, trapezoidal membership function and triangular membership function, and a knowledge base and a rule base are established, so as to adopt different warning times for environmental indicators in different growth periods, thereby reducing the false alarm rate and interference frequency.

[0193] An embodiment of the present invention provides an intelligent environmental monitoring method for under-forest planting, as Figure 5 shown, including:

[0194] Step 1: Deploy a sensor cluster;

[0195] Step 2: Through the sensor cluster, conduct intelligent environmental monitoring of under-forest planting to obtain under-forest monitoring data;

[0196] Step 3: Based on deep learning technology, perform intelligent irrigation according to the under-forest monitoring data;

[0197] Step 4: Based on fuzzy control technology, conduct intelligent environmental warning according to the under-forest monitoring data.

[0198] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. The intelligent environmental monitoring system for understory planting is characterized by: include: A sensor deployment subsystem, used to deploy sensor clusters; The understory monitoring data acquisition subsystem is used to conduct intelligent understory planting environment monitoring and acquire understory monitoring data through sensor clusters; Intelligent sprinkler control subsystem, which is used to perform intelligent sprinkler irrigation based on deep learning technology and forest monitoring data; Intelligent early warning subsystem, which is used to carry out intelligent environmental early warning based on forest monitoring data based on fuzzy control technology; Intelligent sprinkler control subsystem, including: Intelligent irrigation model building module, used to build intelligent irrigation models based on deep learning technology; Sprinkler control module, used for intelligent sprinkler irrigation based on intelligent irrigation model and forest monitoring data; Among them, the intelligent irrigation model building module includes: The first training submodule is used to collect historical monitoring environment indicators during non-irrigation periods, capture the temporal changes of historical monitoring environments during non-irrigation periods, and train an irrigation start model; The second training submodule is used to collect historical monitoring environment indicators during irrigation, capture the temporal changes of historical monitoring environment during irrigation, and train the irrigation shutdown model; An integration module, for obtaining an intelligent irrigation model according to an irrigation on model and an irrigation off model; Among them, the sprinkler control module includes: The irrigation start time determination submodule is used to use the LSTM model to perform multi-time step prediction output when irrigation is not turned on. When the predicted relative humidity of the air reaches the preset first rule condition, the length of the first time step is counted to determine the irrigation start time; The irrigation shut-off time determination submodule is used to use the LSTM model to perform multi-time step prediction output when irrigation is turned on. When the predicted relative humidity of the air reaches the preset second rule condition, the length of the second time step is counted to determine the irrigation shut-off time; The basic computational unit of the LSTM model is as follows: I t =σ(X t W xi +H t-1 W hi +b i ) F t =σ(X t W xf +H t-1 W hf +b f ) O t =σ(X t W xo +H t-1 W ho +b o ) H t =O t ⊙tanh(C t ) Y=H t ⊙W xy +b y Among them, I t 、F t , O t They are the input gate, forget gate, and output gate features at time t, respectively. C t They are candidate memory cells and memory cells at time t, respectively. xi , W hi , W xf , W hf , W xo , W ho , W xc , W hc , W xy , b i , b f , b o , b c , b y are model parameters, X t is the monitoring environment index characteristic at time t in the time series, H t-1 , H t is the hidden state, Y is the relative humidity of the air at time t+1; The smart irrigation model building module also performs the following operations: Obtain the first artificial cultivation record of the target planting base; Based on a preset cultivation feature extraction template, extract a first artificial cultivation feature; the first artificial cultivation feature includes: a first irrigation timing, a first irrigation parameter and a first irrigation effect; Screening the first artificial cultivation record whose first irrigation effect is greater than or equal to a preset irrigation effect threshold and using it as the first target artificial cultivation record; Connect to the big data supplement node to obtain the second artificial cultivation record of the same species as the understory plants; Based on the cultivation feature extraction template, extracting a second artificial cultivation feature; the second artificial cultivation feature includes: a second irrigation timing, a second irrigation parameter, and a second irrigation effect; Screening the second artificial cultivation records whose second irrigation effect is greater than or equal to a preset irrigation effect threshold and using them as the second target artificial cultivation records; Performing a first suitability analysis on the irrigation environment at the second irrigation time, and determining whether the first suitability analysis is passed; Performing a second suitability analysis on the second irrigation parameter, and determining whether the second suitability analysis passes; If both the first suitability analysis and the second suitability analysis are passed, the corresponding second target artificial cultivation record will be used as the third target artificial cultivation record; Based on deep learning technology, the intelligent irrigation model is trained according to the first target artificial cultivation records and the third target artificial cultivation records; The second suitability analysis is performed on the second irrigation parameter, and judging whether the second suitability analysis is passed includes: determining, according to the irrigation capacity of the irrigation device, whether the second irrigation parameter can be achieved; If this can be achieved, the second suitability analysis is passed; The performing a first suitability analysis on the irrigation environment at the second irrigation time and judging whether the first suitability analysis is passed includes: Acquire first environmental characteristic data at a first irrigation time, and determine environmental characteristic data intervals of different first environmental characteristic types according to the first environmental characteristic data; Acquire second environmental characteristic data at a second irrigation opportunity; Determining a matching interval of the second environmental feature data in the environmental feature data interval according to the second environmental feature type of the second environmental feature data; Determine whether the second environmental feature data falls within the matching interval, and if so, obtain a first target weight of the first environmental feature type corresponding to the matching interval; If not, obtaining a second target weight of the first environmental feature type corresponding to the matching interval; Get the data distribution of the matching interval; Based on the percentile method and data distribution, determine the benchmark interval value of the matching interval; Determine the difference between the second environment characteristic data and the reference interval value, and calculate the absolute value of the difference between the difference value and the length of the matching interval; According to the quotient of the absolute value and the length of the matching interval, the weight of the second target is lowered; Determining the environmental feature reproducibility according to the sum of the first target weight corresponding to the second environmental feature type and / or the second target weight after being adjusted down; If the environmental feature reproducibility is greater than or equal to a preset environmental feature reproducibility threshold, the first suitability analysis is passed.

2. The intelligent environment monitoring system for understory planting according to claim 1, characterized in that: Sensor deployment subsystem, including: A location determination module is provided to determine the on-site upwind location of the target planting base for understory planting; The deployment module is used to deploy a sensor cluster at an upwind location on site; wherein the deployed sensor cluster includes: a light sensor, an air temperature and humidity sensor, a carbon dioxide sensor, a soil temperature sensor, and a soil moisture sensor.

3. The intelligent environment monitoring system for understory planting according to claim 1, characterized in that: The understory monitoring data acquisition subsystem includes: The understory monitoring data acquisition module is used to obtain understory monitoring data through a sensor cluster based on a preset monitoring cycle and a cloud server.

4. The intelligent environment monitoring system for understory planting according to claim 1, characterized in that: Intelligent early warning subsystem, including: Membership function design module, used to design membership functions based on the growth environment requirements of understory planting targets; A fuzzy quantification result determination module is used to perform fuzzy quantization on the forest understory monitoring data according to the membership function and determine the fuzzy quantization result; A knowledge rule base construction module is used to construct a knowledge rule base based on expert experience and planting experience; A fuzzy reasoning module is used to perform fuzzy reasoning based on the fuzzy quantification results and the knowledge rule base to obtain fuzzy output quantities; The fuzzy warning module is used to make fuzzy judgments and fuzzy warnings based on the fuzzy output.

5. An intelligent environmental monitoring method for understory planting, characterized by comprising: Step 1: Deploy sensor clusters; Step 2: Use sensor clusters to conduct intelligent environmental monitoring of understory planting and obtain understory monitoring data; Step 3: Based on deep learning technology and forest monitoring data, intelligent sprinkler irrigation is carried out; Step 4: Based on fuzzy control technology, carry out intelligent environmental early warning according to forest monitoring data; Step 3: Based on deep learning technology and forest monitoring data, intelligent sprinkler irrigation is performed, including: Build intelligent irrigation models based on deep learning technology; Based on the intelligent irrigation model, intelligent sprinkler irrigation is carried out according to the forest monitoring data; Among them, based on deep learning technology, an intelligent irrigation model is built, including: Collect historical monitoring environment indicators during non-irrigation periods, capture the temporal changes of historical monitoring environments during non-irrigation periods, and train irrigation start-up models; Collect historical monitoring environment indicators during irrigation, capture the temporal changes of historical monitoring environment during irrigation, and train irrigation shutdown models; According to the irrigation on model and the irrigation off model, an intelligent irrigation model is obtained; Among them, based on the intelligent irrigation model and according to the forest monitoring data, intelligent sprinkler irrigation is carried out, including: When irrigation is not turned on, the LSTM model is used to perform multi-time step prediction output. When the predicted relative humidity of the air reaches the preset first rule condition, the length of the first time step is counted to determine the irrigation start time; When irrigation is turned on, the LSTM model is used to perform multi-time-step prediction output. When the predicted relative humidity of the air reaches the preset second rule condition, the length of the second time step is counted to determine the irrigation shutdown time. The basic computational unit of the LSTM model is as follows: I t =σ(X t W xi +H t-1 W hi +b i ) F t =σ(X t W xf +H t-1 W hf +b f ) O t =σ(X t W xo +H t-1 W ho +b o ) H t =O t ⊙tanh(C t ) Y=H t ⊙W xy +b y Among them, I t 、F t , O t They are the input gate, forget gate, and output gate features at time t, respectively. C t They are candidate memory cells and memory cells at time t, respectively. xi , W hi , W xf , W hf , W xo , W ho , W xc , W hc , W xy , b i , b f , b o , b c , b y are model parameters, X t is the monitoring environment index characteristic at time t in the time series, H t-1 , H t is the hidden state, Y is the relative humidity of the air at time t+1; Based on deep learning technology, the intelligent irrigation model is constructed, which also includes: Obtain the first artificial cultivation record of the target planting base; Based on a preset cultivation feature extraction template, extract a first artificial cultivation feature; the first artificial cultivation feature includes: a first irrigation timing, a first irrigation parameter and a first irrigation effect; Screening the first artificial cultivation record whose first irrigation effect is greater than or equal to a preset irrigation effect threshold value and using it as the first target artificial cultivation record; Connect to the big data supplement node to obtain the second artificial cultivation record of the same species as the understory plants; Based on the cultivation feature extraction template, extracting a second artificial cultivation feature; the second artificial cultivation feature includes: a second irrigation timing, a second irrigation parameter, and a second irrigation effect; Screening the second artificial cultivation records whose second irrigation effect is greater than or equal to a preset irrigation effect threshold and using them as the second target artificial cultivation records; Performing a first suitability analysis on the irrigation environment at the second irrigation time, and determining whether the first suitability analysis is passed; Performing a second suitability analysis on the second irrigation parameter, and determining whether the second suitability analysis passes; If both the first suitability analysis and the second suitability analysis are passed, the corresponding second target artificial cultivation record will be used as the third target artificial cultivation record; Based on deep learning technology, the intelligent irrigation model is trained according to the first target artificial cultivation records and the third target artificial cultivation records; The second suitability analysis is performed on the second irrigation parameter, and judging whether the second suitability analysis is passed includes: determining, according to the irrigation capacity of the irrigation device, whether the second irrigation parameter can be achieved; If this can be achieved, the second suitability analysis is passed; The performing a first suitability analysis on the irrigation environment at the second irrigation time and judging whether the first suitability analysis is passed includes: Acquire first environmental characteristic data at a first irrigation time, and determine environmental characteristic data intervals of different first environmental characteristic types according to the first environmental characteristic data; Acquire second environmental characteristic data at a second irrigation opportunity; Determining a matching interval of the second environmental feature data in the environmental feature data interval according to the second environmental feature type of the second environmental feature data; Determine whether the second environmental feature data falls within the matching interval, and if so, obtain a first target weight of the first environmental feature type corresponding to the matching interval; If not, obtaining a second target weight of the first environmental feature type corresponding to the matching interval; Get the data distribution of the matching interval; Based on the percentile method and data distribution, determine the benchmark interval value of the matching interval; Determine the difference between the second environment characteristic data and the reference interval value, and calculate the absolute value of the difference between the difference value and the length of the matching interval; According to the quotient of the absolute value and the length of the matching interval, the weight of the second target is lowered; Determining the environmental feature reproducibility according to the sum of the first target weight corresponding to the second environmental feature type and / or the second target weight after being adjusted down; If the environmental feature reproducibility is greater than or equal to a preset environmental feature reproducibility threshold, the first suitability analysis is passed.

6. The method for monitoring the understory planting intelligent environment according to claim 5, characterized in that: Step 1: Deploy the sensor cluster, including: Determine the on-site upwind location of the target planting site for understory planting; A sensor cluster is deployed at an upwind location on site; wherein the deployed sensor cluster includes: a light sensor, an air temperature and humidity sensor, a carbon dioxide sensor, a soil temperature sensor, and a soil moisture sensor.

7. The method for monitoring the understory planting environment according to claim 5, characterized in that: Step 2: Use the sensor cluster to conduct intelligent environmental monitoring of forest planting and obtain forest monitoring data, including: Based on the preset monitoring cycle and cloud server, forest monitoring data is obtained through sensor clusters.

8. The method for monitoring the understory planting environment according to claim 5, characterized in that: Step 4: Based on fuzzy control technology and forest monitoring data, intelligent environmental warning is carried out, including: Design membership functions based on the growth environment requirements of understory planting targets; According to the membership function, the understory monitoring data is fuzzy quantified to determine the fuzzy quantification result; Build a knowledge rule base based on expert experience and planting experience; Perform fuzzy reasoning based on fuzzy quantification results and knowledge rule base to obtain fuzzy output; Make fuzzy judgment and fuzzy warning based on fuzzy output.

Images