Intelligent drip irrigation system and method for vegetable greenhouse

Abstract

The invention relates to the technical field of intelligent drip irrigation, and discloses an intelligent drip irrigation system and method for a vegetable greenhouse, and the method comprises the steps: obtaining the growth information and environment information of each vegetable crop in the vegetable greenhouse, carrying out the region recognition of the vegetable greenhouse according to the growth information and environment information, and determining a region to be subjected to drip irrigation and a region not to be subjected to drip irrigation; acquiring growth characteristic parameters and historical water and fertilizer drip irrigation strategies of the vegetable crops in the to-be-irrigated area, and determining growth pathology of the vegetable crops in the to-be-irrigated area according to the growth characteristic parameters, the environment information and the historical water and fertilizer drip irrigation strategies; based on the growth pathology and the environment information, determining fertilizer components and drip irrigation amount, and determining a water-fertilizer ratio according to chemical characteristic parameters of each component of the fertilizer and the drip irrigation amount; preparing water-fertilizer drip irrigation liquid according to the fertilizer components and the water-fertilizer proportion, and performing drip irrigation of the water-fertilizer drip irrigation liquid on the to-be-drip-irrigated area according to the drip irrigation amount. Accurate irrigation is achieved, and the water and fertilizer utilization rate during irrigation of the vegetable greenhouse is increased.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent drip irrigation, in particular to an intelligent drip irrigation system and method for a vegetable greenhouse. BACKGROUND

[0002] The existing vegetable greenhouse drip irrigation system mostly adopts a timing and quantitative irrigation method, lacking dynamic response capability to the real-time growth state of crops and environmental changes. Due to the inability to accurately irrigate according to the differentiated needs of crops in different areas, it is easy to cause excessive water supply in some areas and insufficient water supply in some areas, not only reducing the water resource utilization rate, but also causing uneven growth of crops, affecting the overall yield and quality.

[0003] At present, in the aspect of water and fertilizer management, the existing technology generally fertilizes according to experience or fixed formula, lacking a dynamic adjustment mechanism based on real-time crop nutrient demand and soil nutrient condition. This method is easy to cause low fertilizer utilization rate, on the one hand, leading to waste of nitrogen, phosphorus, potassium and other nutrients and increasing production cost, on the other hand, it may also cause soil salinization and environmental problems such as non-point source pollution, which long-term affects the ecological balance of greenhouse soil. In addition, the recognition of crop growth pathology in traditional systems mostly relies on manual observation, which has lag and subjectivity, and it is difficult to find early problems such as water and fertilizer deficiency or nutrient imbalance in time.

[0004] Therefore, an intelligent irrigation technology for a vegetable greenhouse is urgently needed to solve the problem that the accuracy of water and fertilizer supply in the prior art is insufficient, which limits the further improvement of facility agriculture in water saving, fertilizer saving and quality and efficiency improvement. SUMMARY

[0005] In view of this, the present application provides an intelligent drip irrigation system and method for a vegetable greenhouse, aiming to solve the problem that the accuracy of water and fertilizer supply in the current technology is insufficient, which limits the further improvement of facility agriculture in water saving, fertilizer saving and quality and efficiency improvement.

[0006] The present application provides an intelligent drip irrigation method for a vegetable greenhouse, comprising:

[0007] Obtain growth information and environmental information of each vegetable crop in the vegetable greenhouse, and identify the vegetable greenhouse according to the growth information and the environmental information, to determine the drip irrigation area and the non-drip irrigation area;

[0008] Obtain the growth characteristic parameters of each vegetable crop in the drip irrigation area and the historical water and fertilizer drip irrigation strategy, determine the growth pathology of the vegetable crop in the drip irrigation area according to the growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategy;

[0009] Determine the fertilizer components and the drip irrigation amount based on the growth pathology and the environmental information, and determine the water and fertilizer ratio according to the chemical characteristic parameters of each component of the fertilizer and the drip irrigation amount;

[0010] According to the fertilizer components and the water-fertilizer ratio, water-fertilizer drip irrigation liquid is prepared, and the water-fertilizer drip irrigation liquid is drip irrigated on the to-be-drip-irrigated area according to the drip irrigation amount.

[0011] Further, when acquiring the growth information and the environmental information of the vegetable crops in the vegetable greenhouse, the method comprises:

[0012] Acquiring growth characteristic parameters of the vegetable crops, and determining growth stage information of the vegetable crops according to the growth characteristic parameters, wherein the growth characteristic parameters comprise plant height information, leaf area information, chlorophyll content information and canopy coverage information of the vegetable crops;

[0013] Acquiring environmental parameters and soil parameters in the vegetable greenhouse, wherein the environmental parameters comprise air temperature, air humidity, light parameters and carbon dioxide concentration in the vegetable greenhouse, and the soil parameters comprise soil humidity, soil temperature, soil pH value, soil electrical conductivity and soil chemical component content.

[0014] Further, when determining the to-be-drip-irrigated area and the non-drip-irrigated area according to the growth information and the environmental information, the method comprises:

[0015] Standardizing the acquired growth information and environmental information of the vegetable crops, and interpolating and filling missing data, to construct a spatiotemporal continuous dataset in the vegetable greenhouse;

[0016] According to the spatiotemporal continuous dataset, the greenhouse area is divided into a plurality of sub-areas based on a spatial clustering method, wherein each sub-area has similar crop growth state and environmental characteristics;

[0017] For each sub-area, a drip irrigation state of the sub-area is determined according to a set soil humidity threshold, a lower limit of chlorophyll content and a historical water use response model, and a to-be-drip-irrigated area and a non-drip-irrigated area are determined according to the drip irrigation state of each sub-area.

[0018] Further, for each sub-area, when determining the drip irrigation state of the sub-area according to the set soil humidity threshold, the lower limit of chlorophyll content and the historical water use response model, the method comprises:

[0019] According to the spatiotemporal continuous dataset of the sub-area, a soil humidity value, a chlorophyll content value and historical water use response data of the sub-area are extracted respectively;

[0020] According to a relationship between the soil humidity value and a preset soil humidity value configured, a humidity state value of the sub-area is determined;

[0021] According to a relationship between the chlorophyll content value and a preset lower limit of chlorophyll content configured, a nutrient state value of the sub-area is determined;

[0022] The historical water response data is substituted into a historical water response model constructed based on crop growth response to determine a water shortage risk score of the sub-region;

[0023] According to the humidity state value, the nutrient state value and the water shortage risk score of the sub-region, a drip irrigation state of the sub-region is determined, wherein:

[0024] The humidity state value of the sub-region is compared with a preset humidity state value configured, and a Boolean flag of the humidity state is determined according to a comparison result;

[0025] The nutrient state value of the sub-region is compared with a preset nutrient state value configured, and a Boolean flag of the nutrient state is determined according to a comparison result;

[0026] The water shortage risk score of the sub-region is compared with a preset water shortage risk score configured, and a Boolean flag of the water shortage risk is determined according to a comparison result;

[0027] The Boolean flag of the humidity state, the Boolean flag of the nutrient state and the Boolean flag of the water shortage risk are aggregated based on an AND logic rule configured;

[0028] According to an aggregation result, a drip irrigation state of the sub-region is determined, wherein the drip irrigation state includes a no-drip irrigation state, a water-supply-only drip irrigation state, a fertilizer-application-only drip irrigation state, a water-and-fertilizer integrated drip irrigation state and an emergency drip irrigation state.

[0029] Further, when the drip irrigation state of each sub-region is determined, the to-be-drip-irrigated region and the non-drip-irrigated region are determined, including:

[0030] The drip irrigation state of each sub-region is obtained, and the to-be-drip-irrigated region and the non-drip-irrigated region are determined according to the drip irrigation state, wherein:

[0031] If the drip irrigation state of the sub-region is the no-drip irrigation state, the sub-region is determined as the non-drip-irrigated region;

[0032] If the drip irrigation state of the sub-region is the water-supply-only drip irrigation state, the fertilizer-application-only drip irrigation state, the water-and-fertilizer integrated drip irrigation state or the emergency drip irrigation state, the sub-region is determined as the to-be-drip-irrigated region.

[0033] Further, when the growth characteristic parameters and the environmental information and the historical water-and-fertilizer drip irrigation strategy of the to-be-drip-irrigated region are determined, the growth pathology of the vegetable crop in the to-be-drip-irrigated region is determined, including:

[0034] The growth characteristic parameters, the environmental information and the historical water-and-fertilizer drip irrigation strategy of each vegetable crop in the to-be-drip-irrigated region are obtained, and the growth characteristic parameters, the environmental information and the historical water-and-fertilizer drip irrigation strategy are normalized;

[0035] According to the normalized growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategies, a water deficiency value, a nitrogen deficiency value, a phosphorus deficiency value, a potassium deficiency value and a salinity stress score of the to-be-irrigated region are determined;

[0036] A relationship between the water deficiency value, the nitrogen deficiency value, the phosphorus deficiency value, the potassium deficiency value and the salinity stress score of the to-be-irrigated region and corresponding preset threshold values is determined to determine a pathological feature of the to-be-irrigated region.

[0037] The pathological feature is matched with each preset pathological feature in the configured crop growth pathological feature set, and according to a matching result, a growth pathology of each vegetable crop in the to-be-drip-irrigated region is determined, wherein:

[0038] A feature similarity between the pathological feature and each preset pathological feature is obtained, each feature similarity is arranged in a reverse order, and a first corresponding preset pathological feature in the feature similarity arrangement is determined as the pathological feature of the to-be-irrigated region.

[0039] Further, when the crop growth pathological feature set is configured, the following steps are included:

[0040] Each growth pathology type of each vegetable crop and corresponding growth characteristic parameters, environmental information and soil water and fertilizer content of each growth pathology type are obtained.

[0041] According to each growth pathology type of the vegetable and the corresponding growth characteristic parameters, environmental information and soil water and fertilizer content of each growth pathology type, a growth pathology correlation formula of the vegetable is established.

[0042] A distance measure between each growth pathology correlation formula is obtained, and a distance matrix is established according to the distance measure.

[0043] Each growth pathology correlation formula is iteratively clustered according to the distance matrix, and a pathological feature vector of each growth pathology type of the vegetable is determined according to a clustering result.

[0044] According to the pathological feature vector of each growth pathology type of each vegetable, a crop growth pathological feature set is established.

[0045] Further, based on the growth pathology and the environmental information, when determining the fertilizer components and the drip irrigation amount, the following steps are included:

[0046] The growth pathology is matched with a preset nutrient demand database to generate an initial fertilizer component demand.

[0047] According to the environmental information, a crop transpiration amount and a soil evaporation amount are obtained, and the initial fertilizer component demand is corrected.

[0048] The corrected fertilizer component demand, the crop transpiration amount, the soil evaporation amount and the soil water storage amount are used to determine a basic drip irrigation amount.

[0049] According to the modified fertilizer component demand and the basic drip irrigation amount, the fertilizer component and the drip irrigation amount of the drip irrigation area are determined.

[0050] Further, according to the chemical characteristic parameters of each component of the fertilizer and the drip irrigation amount, when the water-fertilizer ratio is determined, the following is included:

[0051] Based on the effective nutrient content of each component of the fertilizer, the drip irrigation amount and the target fertilization amount of the drip irrigation area, the target concentration of each nutrient in the drip irrigation liquid is determined.

[0052] Based on the target concentration vector and the contribution parameters of the unit concentration of each component of the fertilizer to the EC and pH, the predicted EC value and the pH value of the target solution are determined.

[0053] According to the relationship between the target concentration vector, the predicted EC / pH and the solubility and compatibility parameters of the fertilizer, the water-fertilizer matching scheme is determined.

[0054] Compared with the prior art, the beneficial effects of the present application are that by obtaining the growth information and environmental information of each crop in the vegetable greenhouse and based thereon performing regional identification, the accurate division of the irrigation area and the non-irrigation area is realized, and the problems of water resource waste and uneven crop growth caused by flood irrigation or unified irrigation of the whole area are avoided. When the drip irrigation area is managed, the growth characteristic parameters of the crops, the environmental information and the historical water-fertilizer drip irrigation strategy are combined, the growth pathology of the crops can be accurately identified, and therefore the water-fertilizer supply scheme can be developed in a targeted manner, and the scientificity and timeliness of the water-fertilizer management are improved. By reasonably determining the fertilizer component and the drip irrigation amount based on the growth pathology and the environmental information, and optimizing the water-fertilizer ratio in combination with the chemical characteristic parameters of the fertilizer, the method not only can meet the nutrient demand of the crops in different growth stages, but also can effectively prevent the soil salinization and environmental pollution caused by excessive fertilization, and significantly improve the water-fertilizer utilization efficiency. Finally, the drip irrigation liquid is prepared according to the optimized water-fertilizer ratio and the accurate drip irrigation is implemented, which not only can promote the healthy and balanced growth of the crops, improve the yield and quality, but also can save the water and fertilizer input, reduce the production cost, and has significant economic and ecological benefits.

[0055] On the other hand, the present application also provides an intelligent drip irrigation system for a vegetable greenhouse, comprising:

[0056] The acquisition module is configured to obtain the growth information and environmental information of each vegetable crop in the vegetable greenhouse, and to perform regional identification on the vegetable greenhouse according to the growth information and environmental information, and to determine the drip irrigation area and the non-drip irrigation area. The acquisition module is also configured to obtain the growth characteristic parameters of each vegetable crop in the drip irrigation area and the historical water-fertilizer drip irrigation strategy.

[0057] The analysis module is electrically connected with the acquisition module, and is configured to determine a growth pathology of the vegetable crop in the to-be-irrigated region according to the growth characteristic parameter, the environmental information and a historical water and fertilizer drip irrigation strategy; the analysis module is further configured to determine a fertilizer component and a drip irrigation amount based on the growth pathology and the environmental information, and to determine a water and fertilizer ratio according to a chemical characteristic parameter of each component of the fertilizer and the drip irrigation amount.

[0058] The control module is electrically connected with the analysis module, and is configured to prepare water and fertilizer drip irrigation liquid according to the fertilizer component and the water and fertilizer ratio, and to drip irrigate the water and fertilizer drip irrigation liquid to the to-be-drip-irrigated region according to the drip irrigation amount.

[0059] It can be understood that the intelligent drip irrigation system and method for a vegetable greenhouse in one of the above embodiments of the present application have the same beneficial effects, which will not be described again. BRIEF DESCRIPTION OF DRAWINGS

[0060] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments and are not intended to limit the scope of the application. Moreover, the same reference numerals are used throughout the same figures. In the drawings:

[0061] Figure 1 A flow chart of an intelligent drip irrigation method for a vegetable greenhouse provided by an embodiment of the present application;

[0062] Figure 2 A flow chart of an intelligent drip irrigation method for a vegetable greenhouse provided by an embodiment of the present application;

[0063] Figure 3 A functional block diagram of an intelligent drip irrigation system for a vegetable greenhouse provided by an embodiment of the present application. DETAILED DESCRIPTION

[0064] Exemplary embodiments of the present disclosure will be described in detail with reference to the drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0065] As shown in Figures 1-2 In some embodiments of the present application, the present embodiment provides an intelligent drip irrigation method for a vegetable greenhouse, comprising:

[0066] In step S100, growth information and environment information of each vegetable crop in the vegetable greenhouse are acquired, and the vegetable greenhouse is regionally identified according to the growth information and the environment information to determine the drip irrigation region and the non-drip irrigation region.

[0067] Specifically, when the growth information and the environment information of each vegetable crop in the vegetable greenhouse are acquired, the growth characteristic parameters of each vegetable crop are acquired, and the growth stage information of each vegetable crop is determined according to the growth characteristic parameters, wherein the growth characteristic parameters include the plant height information, the leaf area information, the chlorophyll content information and the canopy coverage information of the vegetable crop; the environment parameters and the soil parameters in the vegetable greenhouse are acquired, wherein the environment parameters include the air temperature, the air humidity, the light parameter and the carbon dioxide concentration in the vegetable greenhouse, and the soil parameters include the soil humidity, the soil temperature, the soil pH value, the soil electrical conductivity and the soil chemical component content.

[0068] Specifically, when the vegetable greenhouse is regionally identified according to the growth information and the environment information to determine the drip irrigation region and the non-drip irrigation region, the acquired growth information and the environment information of the vegetable crop are standardized and the missing data is interpolated and filled, and a time-space continuous data set in the vegetable greenhouse is constructed; according to the time-space continuous data set, the greenhouse region is divided into multiple sub-regions based on the spatial clustering method, wherein each sub-region has similar crop growth state and environment characteristics; for each sub-region, the drip irrigation state of each sub-region is determined according to the set soil humidity threshold, the lower limit of chlorophyll content and the historical water response model, and the drip irrigation region and the non-drip irrigation region are determined according to the drip irrigation state of each sub-region.

[0069] Specifically, for each sub-region, according to the set soil moisture threshold, the lower limit of chlorophyll content and the historical water response model, the drip irrigation state of each sub-region is determined, including: according to the spatio-temporal data set of the sub-region, the soil moisture value, the chlorophyll content value and the historical water response data of the sub-region are extracted respectively; according to the relationship between the soil moisture value and the configured preset soil moisture value, the humidity state value of the sub-region is determined; according to the relationship between the chlorophyll content value and the configured preset lower limit of chlorophyll content, the nutrient state value of the sub-region is determined; the historical water response data is substituted into the historical water response model based on the crop growth response to determine the water shortage risk score of the sub-region; according to the humidity state value, the nutrient state value and the water shortage risk score of the sub-region, the drip irrigation state of the sub-region is determined, wherein: the humidity state value of the sub-region is compared with the configured preset humidity state value, and the Boolean mark of the humidity state is determined according to the comparison result; the nutrient state value of the sub-region is compared with the configured preset nutrient state value, and the Boolean mark of the nutrient state is determined according to the comparison result; the water shortage risk score of the sub-region is compared with the configured preset water shortage risk score, and the Boolean mark of the water shortage risk is determined according to the comparison result; the Boolean marks of the humidity state, the nutrient state and the water shortage risk are aggregated based on the configured AND logic rule; according to the aggregation result, the drip irrigation state of the sub-region is determined, wherein the drip irrigation state includes no drip irrigation state, only water supplement drip irrigation state, only fertilizer application drip irrigation state, water and fertilizer integrated drip irrigation state and emergency drip irrigation state.

[0070] Specifically, according to the drip irrigation state of each sub-region, the drip irrigation region and the non-drip irrigation region are determined, including: obtaining the drip irrigation state of each sub-region, and determining the drip irrigation region and the non-drip irrigation region according to the drip irrigation state, wherein: if the drip irrigation state of the sub-region is no drip irrigation state, then the sub-region is determined as a non-drip irrigation region; if the drip irrigation state of the sub-region is only water supplement drip irrigation state, only fertilizer application drip irrigation state, water and fertilizer integrated drip irrigation state or emergency drip irrigation state, then the sub-region is determined as a drip irrigation region.

[0071] It can be understood that in the information collection stage, the growth characteristic parameters of each vegetable crop are obtained in real time by using multiple types of sensors and monitoring devices arranged in the greenhouse, including plant height, leaf area, chlorophyll content, and canopy coverage. These parameters not only reflect the growth vigor and photosynthetic capacity of the crops, but also can be used to calculate the growth stage of the crops through a model, thereby providing a basis for irrigation strategies. At the same time, environmental parameters such as air temperature, humidity, light intensity, and carbon dioxide concentration, as well as soil parameters such as soil moisture, soil temperature, pH value, electrical conductivity, and chemical component content, are also collected synchronously, forming a complete data chain covering crop growth, environmental conditions, and soil conditions. Secondly, in the data preprocessing and modeling stage, the collected multi-source data is standardized to eliminate the influence of different sensor measurement ranges and unit differences; for missing data, time interpolation, spatial interpolation, or multivariate regression is used for filling to ensure the continuity and integrity of the data. On this basis, a data set with spatial and temporal continuity characteristics is constructed, so that each data point not only has time series properties, but also has spatial location correlation. This data set provides high-quality input for subsequent spatial clustering analysis. Subsequently, in the region identification stage, the method uses spatial clustering algorithms (such as density-based DBSCAN or center-based K-Means improved algorithm) to divide the greenhouse into several sub-regions, so that the crops in the same region are as consistent as possible in growth status, environmental conditions, and soil characteristics. This can avoid the "flood irrigation" or "one-size-fits-all" irrigation method, making water and fertilizer management more targeted. In the drip irrigation state determination stage, key indicators are extracted from the spatio-temporal data set of each sub-region: soil moisture value, chlorophyll content value, and historical water response data. By comparing with the preset soil moisture threshold and chlorophyll content lower limit, the humidity state value and nutrient state value are obtained respectively; then the historical water response data is substituted into the response model based on crop growth response to calculate the water shortage risk score. These three indicators are respectively subjected to Boolean judgment (high / low, sufficient / insufficient, at risk / no risk), and are aggregated through the set AND logic rule, thereby obtaining a clear classification of the drip irrigation state, including no need for drip irrigation, only water supplement, only fertilizer application, water and fertilizer integrated drip irrigation, and emergency drip irrigation. Finally, according to the drip irrigation state of each sub-region, the greenhouse is automatically divided into drip irrigation regions and non-drip irrigation regions, and appropriate irrigation strategies and water-fertilizer ratios are matched for each drip irrigation region. This data-driven decision-making approach can significantly improve water and fertilizer utilization efficiency, reduce resource waste, and reduce the risk of diseases caused by excessive irrigation or nutrient deficiency, thereby realizing the intelligent landing of precision agriculture.

[0072] It can be seen that through the sensor network and monitoring equipment, the growth characteristics parameters of vegetable crops such as plant height, leaf area, chlorophyll content, and canopy coverage, as well as environmental parameters such as air temperature and humidity, light, and carbon dioxide concentration, and soil parameters such as soil moisture, temperature, pH, conductivity, and chemical composition are synchronously acquired, and based on this, the growth stage and growth status of the crops are determined. This step provides comprehensive and accurate input data for subsequent regional identification. In the data processing link, the collected crop growth information and environmental information are standardized, missing values are filled using interpolation methods, and a time-continuous and spatially-related spatiotemporal data set is constructed. Based on this data set, a spatial clustering algorithm is applied to divide the greenhouse into sub-regions, so that the growth status and environmental conditions within each sub-region are as consistent as possible, thereby laying the foundation for differentiated drip irrigation decision-making. In the drip irrigation state determination process, the method combines the set soil moisture threshold, chlorophyll content lower limit, and historical water use response model to calculate the humidity state value, nutrient state value, and water shortage risk score, respectively, and compares these values with the preset standards using Boolean comparison. Subsequently, the Boolean labels of humidity, nutrients, and water shortage risk are aggregated using AND logic rules to obtain the drip irrigation state classification of each sub-region, including no need for drip irrigation, only water replenishment, only fertilizer application, water and fertilizer integration, and emergency drip irrigation. Finally, according to the drip irrigation state of each sub-region, the greenhouse is divided into drip irrigation and non-drip irrigation regions, achieving precise water and fertilizer supply based on the actual needs of crops. The core of this principle is to combine multi-dimensional agricultural big data with model calculations, use logic determination and spatial analysis techniques, and achieve intelligent, fine, and regionalized control of drip irrigation.

[0073] For example, a greenhouse vegetable greenhouse is taken as an example, and various vegetable crops in the greenhouse are precisely identified and controlled. The greenhouse area is about 2000 square meters, and crops such as tomatoes, cucumbers and lettuce are planted. Various sensors are deployed inside the greenhouse, including plant growth sensors for monitoring crop height, leaf area, chlorophyll content and canopy coverage, environmental sensors for collecting air temperature, air humidity, light intensity, carbon dioxide concentration, and soil sensors for monitoring soil moisture, soil temperature, pH value, electrical conductivity and chemical component content. The above sensors are connected to the data acquisition terminal through wireless network, realizing real-time data remote transmission. During operation, first, the growth characteristics parameters such as height, leaf area, chlorophyll content and canopy coverage of each monitoring point are collected by the crop growth sensor, and the growth stage of the crop is automatically determined by combining the crop variety and growth cycle model. At the same time, the environmental sensor and the soil sensor synchronously collect air temperature and humidity, light intensity, carbon dioxide concentration, and soil moisture, temperature, pH value, electrical conductivity and other information, forming a set of multi-dimensional raw data covering crop growth, environment and soil conditions. The collected data is standardized, and the missing values are filled by using time interpolation and space interpolation method, and a multi-dimensional data set with time and space continuity is constructed. Then, based on the spatial clustering algorithm (such as improved K-Means clustering), the whole greenhouse area is divided into several sub-regions, so that the crops in the same region are as close as possible in growth state and environmental conditions. For example, in one collection cycle, the greenhouse is divided into 8 sub-regions, among which the soil moisture in the 1st, 2nd and 5th regions is low and the chlorophyll content is low, the soil moisture in the 4th and 7th regions is sufficient but the chlorophyll content is slightly low, and the remaining regions are within the normal range. For each sub-region, the soil moisture value, chlorophyll content value and historical water response data are extracted, and compared with the set soil moisture threshold (such as 25%), chlorophyll content lower limit (such as 35SPAD) and historical water shortage risk score threshold, respectively generating humidity state Boolean label, nutrient state Boolean label and water shortage risk Boolean label. Then, the above Boolean labels are aggregated by using the preset AND logic rule to determine the drip irrigation state of each sub-region. For example, the 1st region is short of water and nutrients and has high water shortage risk, and is determined as "water and fertilizer integrated drip irrigation state"; the 4th region has normal humidity but insufficient nutrients, and is determined as "fertilizer only drip irrigation state"; the 6th region has all normal indicators, and is determined as "no need for drip irrigation state". Finally, according to the drip irrigation state, the sub-regions are marked as drip irrigation region or non-drip irrigation region, and the control command is sent to the automatic drip irrigation, realizing precise water supply, fertilization or water and fertilizer integrated treatment in the corresponding region. Taking the detection results as an example, the 1st, 2nd, 4th, 5th and 7th regions are determined as drip irrigation regions, and the remaining regions are non-drip irrigation regions, thereby realizing precise water use and precise fertilization, and significantly improving resource utilization efficiency.

[0074] In step S200, the growth characteristic parameters of each vegetable crop in the to-be-irrigated region and the historical water and fertilizer drip irrigation strategy are obtained, and the growth pathology of the vegetable crop in the to-be-irrigated region is determined according to the growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategy.

[0075] Specifically, when the growth pathology of the vegetable crop in the to-be-irrigated region is determined according to the growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategy, the growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategy of each vegetable crop in the to-be-irrigated region are obtained, and the growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategy are normalized; the water deficiency value, the nitrogen deficiency value, the phosphorus deficiency value, the potassium deficiency value and the salt stress score of the to-be-irrigated region are determined according to the normalized growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategy; the relationship between the water deficiency value, the nitrogen deficiency value, the phosphorus deficiency value, the potassium deficiency value and the salt stress score of the to-be-irrigated region and the corresponding preset threshold value is determined to determine the pathological characteristics of the to-be-irrigated region; the pathological characteristics are matched with each preset pathological characteristic in the configured crop growth pathology characteristic set, and the growth pathology of each vegetable crop in the to-be-irrigated region is determined according to the matching result, wherein the feature similarity between the pathological characteristics and each preset pathological characteristic is obtained, each feature similarity is arranged in reverse order, and the first corresponding preset pathological characteristic in the feature similarity arrangement is determined as the pathological characteristic of the to-be-irrigated region.

[0076] Specifically, when the crop growth pathology characteristic set is configured, the growth pathology types of each vegetable crop and the growth characteristic parameters, the environmental information and the soil water and fertilizer content corresponding to each growth pathology type are obtained; each growth pathology correlation formula of the vegetable is established according to the growth pathology types of the vegetable and the growth characteristic parameters, the environmental information and the soil water and fertilizer content corresponding to each growth pathology type; the distance measure between each growth pathology correlation formula is obtained, and a distance matrix is established according to the distance measure; each growth pathology correlation formula is iteratively clustered according to the distance matrix, and the pathological characteristic vector of each growth pathology type of the vegetable is determined according to the clustering result; and the crop growth pathology characteristic set is established according to the pathological characteristic vector of each growth pathology type of each vegetable.

[0077] It can be understood that through multi-source data fusion and standardization processing, the growth characteristic parameters, environmental information and historical water and fertilizer drip irrigation strategies of the vegetable crops in the to-be-drip-irrigated region are converted into a quantifiable and comparable index system. Through normalization operation, parameters of different dimensions and different time scales are unified to the same numerical range, ensuring the comparability and accuracy of subsequent calculation. After data processing, the system calculates the water deficiency value, nitrogen deficiency value, phosphorus deficiency value, potassium deficiency value and salt stress score of the to-be-drip-irrigated region respectively by using the quantification model of crop physiological demand and environmental adaptability. These values reflect the actual demand degree of crops for water and nutrients and the level of stress under the current state. By comparing these calculated values with the preset threshold, the key pathological characteristics of crops in the region can be identified, such as water stress, nitrogen deficiency or salt damage. Finally, in order to realize the accuracy and universality of pathological diagnosis, the present scheme pre-constructs a crop growth pathological feature set. The feature set establishes a pathological correlation formula based on the growth characteristic parameters, environmental conditions and soil water and fertilizer content of different vegetable varieties under various pathological types, and through distance measurement and clustering analysis, different pathological characteristics are vectorized to form a standardized pathological feature library for matching. In the diagnosis process, the system calculates the similarity of the current pathological characteristics and each preset pathological characteristic in the library, and selects the pathological type with the highest similarity as the diagnosis result through sorting, thereby realizing accurate pathological recognition based on similarity matching.

[0078] It can be seen that by obtaining the growth characteristic parameters, environmental information and historical water and fertilizer drip irrigation strategies of each vegetable crop in the to-be-drip-irrigated region, combined with normalization processing, effective fusion and unified analysis of multi-dimensional data are realized, improving the compatibility and accuracy of the data. Based on normalized data, the water deficiency value, nitrogen deficiency value, phosphorus deficiency value, potassium deficiency value and salt stress score can be accurately calculated, accurately reflecting the current nutritional and water status of crops and enhancing the scientificity and pertinence of pathological diagnosis. By similarity matching between the calculated pathological characteristics and the preset crop growth pathological feature set, the system can quickly and accurately identify the specific growth pathological condition of crops, realizing dynamic pathological determination based on historical and real-time data. This matching mechanism improves the accuracy of diagnosis and ensures that more reasonable water and fertilizer management strategies are developed for different pathological types. In addition, the constructed crop growth pathological feature set uses correlation formula modeling and iterative clustering method to scientifically divide the feature vectors of different pathological types, enhancing the representativeness and discriminability of pathological characteristics and providing a solid data foundation for subsequent accurate regulation.

[0079] Specifically, first, the growth characteristic parameters such as plant height, leaf area, chlorophyll content and canopy coverage in the drip irrigation area to be irrigated are collected by sensors, and environmental and soil data such as air temperature, humidity, light intensity, CO2 concentration, soil humidity, temperature, pH value, electrical conductivity and nitrogen, phosphorus and potassium content are also collected. The historical water and fertilizer drip irrigation strategy data include the types, amount and irrigation frequency of previous fertilization. Second, the above multi-source data is normalized to eliminate the influence of dimensional differences and abnormal values. Based on the normalized data, the water deficiency value of the region is calculated as 0.25 (threshold value 0.3), the nitrogen deficiency value is 0.45 (threshold value 0.4), the phosphorus deficiency value is 0.15 (threshold value 0.2), the potassium deficiency value is 0.35 (threshold value 0.3), and the salt stress score is 0.1 (threshold value 0.25). It is determined that the region has moderate nitrogen deficiency and potassium deficiency, and the water deficiency is light, and the salt stress is low. Then, these pathological characteristics are compared with the pre-established crop growth pathological characteristic set. The pathological characteristic set is formed by collecting a large amount of pathological data of tomatoes at different growth stages, combining environmental and soil indicators, and forming typical growth pathological types and corresponding characteristic vectors through iterative clustering. The similarity of the current pathological characteristics to each type in the pathological characteristic set is calculated, and it is found that the current data is most similar to the "moderate nitrogen and potassium deficiency type" (highest similarity), so it is determined that the main growth pathology of the tomatoes in the drip irrigation area is moderate nitrogen and potassium deficiency. Based on the determination result, the subsequent water and fertilizer management strategy is adjusted, and the nitrogen and potassium elements are supplemented, and the irrigation amount is appropriately adjusted, so as to promote the healthy growth of crops and improve the yield. Through the above embodiment, the effective application of the technical scheme in multi-source data fusion, pathological characteristic accurate determination and dynamic water and fertilizer management is embodied, which provides scientific basis and technical support for intelligent drip irrigation.

[0080] Step S300, based on the growth pathology and environmental information, determine the fertilizer components and the drip irrigation amount, and determine the water and fertilizer ratio according to the chemical characteristic parameters of each component of the fertilizer and the drip irrigation amount.

[0081] Specifically, when determining the fertilizer components and the drip irrigation amount based on the growth pathology and the environmental information, the growth pathology is matched with a pre-set nutrient demand database to generate an initial fertilizer component demand; the crop transpiration and soil evaporation are obtained according to the environmental information, and the initial fertilizer component demand is corrected; the corrected fertilizer component demand, the crop transpiration, the soil evaporation and the soil water storage capacity are used to determine a basic drip irrigation amount; and the fertilizer components and the drip irrigation amount for the drip irrigation area are determined according to the corrected fertilizer component demand and the basic drip irrigation amount.

[0082] Specifically, according to the chemical characteristic parameters of each component of the fertilizer and the drip irrigation amount, the water-fertilizer ratio is determined, including: based on the effective nutrient content of each component of the fertilizer, the drip irrigation amount and the target fertilization amount of the drip irrigation area to be determined, the target concentration of each nutrient in the drip irrigation liquid is determined; based on the target concentration vector and the contribution parameters of the unit concentration of each component of the fertilizer to the EC and pH, the predicted EC value and the pH value of the target solution are determined; according to the relationship between the target concentration vector, the predicted EC / pH and the solubility and compatibility parameters of the fertilizer, the water-fertilizer ratio scheme is determined.

[0083] It can be understood that by matching the detected growth pathological information with the preset nutrient demand database, the preliminary demand amount of each nutrient of the crop is obtained. This step is based on historical data and crop physiological rules, and ensures that the fertilizer ratio is matched with the actual nutrient demand of the crop. Then, combined with the dynamic water consumption indexes such as crop transpiration and soil evaporation in the environmental information, the initial fertilizer demand is corrected to adapt to the actual water and fertilizer demand of the crop under the current environmental conditions. By combining the corrected fertilizer demand with factors such as soil water storage, the basic drip irrigation amount is calculated to ensure that irrigation meets the water demand and prevents over-irrigation. On this basis, the specific fertilizer component content and drip irrigation amount are determined to form a customized drip irrigation scheme for the drip irrigation area to be determined. Then, based on the effective nutrient content of each fertilizer component, the determined drip irrigation amount and the target fertilization amount, the target concentration of each nutrient in the drip irrigation liquid is calculated to ensure accurate fertilization. By considering the influence of the unit concentration of each fertilizer component on the electrical conductivity (EC) and the pH value, the EC value and the pH value of the target solution are predicted to ensure that the physical and chemical properties of the formula are suitable for plant absorption and do not harm the facilities. Finally, combined with the solubility and compatibility parameters of the fertilizer, the water-fertilizer ratio is reasonably adjusted, and a scientific and reasonable water-fertilizer ratio scheme is developed to realize efficient application of water and fertilizer integration.

[0084] It can be seen that, firstly, by matching the current crop growth pathology with the preset nutrient demand database, the specific demand amount of various nutrients for crops at different growth stages and health states is determined, and the preliminary fertilizer component demand is generated. This step effectively avoids blind fertilization and ensures more accurate nutrient supply for the actual situation of crops. Subsequently, combined with environmental information such as crop transpiration, soil evaporation and soil water storage, the initial fertilizer demand is dynamically corrected, and the fertilizer amount is adjusted to adapt to the changes in environmental conditions. For example, in a high-temperature or low-humidity environment, the crop transpiration is enhanced, and the water and nutrient supply needs to be increased accordingly; otherwise, it needs to be reduced, so as to achieve the effect of water and fertilizer saving. The corrected fertilizer demand and environmental factors together determine the basic drip irrigation amount, ensuring that the water and fertilizer amount output by the drip irrigation system not only meets the growth demand of crops, but also avoids resource waste. In terms of water and fertilizer ratio, based on the effective nutrient content of each component of the fertilizer and the final drip irrigation amount, the target concentration of each nutrient in the drip irrigation liquid is calculated, ensuring that the nutrient content in the fertilization solution is accurate and balanced. At the same time, by using the contribution parameters of fertilizer components to electrical conductivity (EC) and pH value, the electrical conductivity and pH value of the drip irrigation liquid are predicted, and the water and fertilizer matching scheme is further adjusted. This process effectively avoids the problems of fertilizer damage or nutrient deficiency caused by too concentrated or too dilute fertilization solution, and ensures that the chemical properties of the fertilization solution are suitable for the absorption and utilization of crop roots.

[0085] Specifically, by collecting the growth pathology data and environmental parameters of crops in each sub-region, firstly, the collected growth pathology information is matched with the preset nutrient demand database to determine the initial fertilizer component demand required by crops in the region. For example, it is found that the tomato plants in the region have a growth pathology of nitrogen deficiency, and the specific amount of nitrogen fertilizer that needs to be supplemented is preliminarily calculated. Subsequently, combined with real-time environmental information, including air temperature, humidity, crop transpiration and soil evaporation, the initial fertilizer demand is corrected. If the environment shows high temperature and dryness, and the crop transpiration is intensified, the water and nutrient supply amount needs to be increased accordingly, and vice versa. Combined with the detection results of soil water storage, the basic drip irrigation amount is calculated to ensure that the water and fertilizer supply is balanced with the soil water, and over-irrigation or water shortage is prevented. Then, based on the corrected fertilizer demand and the determined basic drip irrigation amount, the specific application concentration of each fertilizer component and the total amount of drip irrigation are determined. Based on this, combined with the effective nutrient content of each component of the fertilizer, the target concentration of each nutrient in the drip irrigation liquid is calculated. At the same time, according to the contribution of fertilizer components to electrical conductivity (EC) and pH value, the chemical properties of the fertilization solution are predicted. Finally, combined with the solubility and compatibility parameters of the fertilizer, the water and fertilizer matching scheme is optimized to ensure that the drip irrigation liquid is nutritionally balanced and has suitable chemical properties. The adjusted water and fertilizer ratio scheme not only meets the growth demand of crops, but also avoids fertilizer waste and root damage, realizing precise and efficient intelligent drip irrigation management.

[0086] Step S400, according to the fertilizer components and the water-fertilizer ratio, prepare the water-fertilizer drip irrigation liquid, and drip irrigate the water-fertilizer drip irrigation liquid to the drip irrigation area according to the drip irrigation amount.

[0087] In the above embodiment, by acquiring the growth information and environmental information of each crop in the vegetable greenhouse, and based on this, the region is identified, the accurate division of the irrigation area and the non-irrigation area is realized, and the water resource waste and the uneven growth of crops caused by flood irrigation or unified irrigation in the whole area are avoided. When managing the drip irrigation area, the method combines the growth characteristic parameters of the crops, the environmental information and the historical water-fertilizer drip irrigation strategy, can accurately identify the growth pathology of the crops, and thus can formulate the water-fertilizer supply scheme, improve the scientificity and timeliness of the water-fertilizer management. By reasonably determining the fertilizer components and the drip irrigation amount based on the growth pathology and the environmental information, and combining the water-fertilizer ratio optimized by the chemical characteristic parameters of the fertilizer components, the method not only can meet the nutritional needs of the crops in different growth stages, but also can effectively prevent the soil salinization and environmental pollution caused by excessive fertilization, and significantly improve the water-fertilizer utilization efficiency. Finally, according to the optimized water-fertilizer ratio, the drip irrigation liquid is prepared and the precise drip irrigation is implemented, which can not only promote the healthy and balanced growth of the crops, improve the yield and quality, but also save the water-fertilizer input, reduce the production cost, and has significant economic and ecological benefits.

[0088] In another preferred mode based on the above embodiment, as shown in Figure 3 The intelligent drip irrigation system for the vegetable greenhouse provided by the present embodiment comprises:

[0089] The acquisition module is configured to acquire the growth information and environmental information of each vegetable crop in the vegetable greenhouse, and to identify the regions of the vegetable greenhouse according to the growth information and environmental information, to determine the drip irrigation area and the non-drip irrigation area. The acquisition module is also configured to acquire the growth characteristic parameters of each vegetable crop in the drip irrigation area and the historical water-fertilizer drip irrigation strategy.

[0090] The analysis module is electrically connected with the acquisition module, and the analysis module is configured to determine the growth pathology of the vegetable crops in the drip irrigation area according to the growth characteristic parameters and environmental information and the historical water-fertilizer drip irrigation strategy. The analysis module is also configured to determine the fertilizer components and the drip irrigation amount based on the growth pathology and the environmental information, and to determine the water-fertilizer ratio according to the chemical characteristic parameters of each component of the fertilizer and the drip irrigation amount.

[0091] The control module is electrically connected with the analysis module, and the control module is configured to prepare the water-fertilizer drip irrigation liquid according to the fertilizer components and the water-fertilizer ratio, and to drip irrigate the water-fertilizer drip irrigation liquid to the drip irrigation area according to the drip irrigation amount.

[0092] It can be understood that the intelligent drip irrigation system and method for the vegetable greenhouse in each of the above embodiments of the present application have the same beneficial effects, which will not be repeated.

[0093] Those skilled in the art will appreciate that embodiments of the application can be supplied as a method, a system or a computer program product. Accordingly, the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the application can be embodied in the form of a computer program product on one or more computer readable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage media, etc.) having computer usable program code embodied thereon.

[0094] The present application is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to embodiments of the application. It should be understood that each flow and / or block in the flowchart and / or block diagrams, as well as a combination of flows and / or blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing device, generate a means for implementing the functions specified in the flowchart and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified in the flow or flows and / or block or blocks.

[0095] These computer program instructions can also be stored in a computer readable storage medium that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a manufacture product including instruction means, which implement the functions specified in the flowchart and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified in the flow or flows and / or block or blocks.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operational steps are performed on the computer or other programmable data processing device to produce a computer implemented process, so that the instructions executed on the computer or other programmable device provide a process for implementing the functions specified in the flowchart and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified in the flow or flows and / or block or blocks.

[0097] Finally, it should be noted that the above embodiments are merely used to illustrate the technical solutions of the present application, but not to limit it. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced, and any modification or replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. An intelligent drip irrigation method for a vegetable greenhouse, characterized in that, The method comprises the following steps: Obtain the growth information and environmental information of each vegetable crop in the vegetable greenhouse, and identify the regions of the vegetable greenhouse according to the growth information and environmental information to determine the drip irrigation region and the non-drip irrigation region; Obtain the growth characteristic parameters and historical water and fertilizer drip irrigation strategies of each vegetable crop in the drip irrigation region, and determine the growth pathology of the vegetable crop in the drip irrigation region according to the growth characteristic parameters, environmental information and historical water and fertilizer drip irrigation strategies; Determine the fertilizer components and drip irrigation amount based on the growth pathology and environmental information, and determine the water and fertilizer ratio according to the chemical characteristic parameters of each component of the fertilizer and the drip irrigation amount; Prepare the water and fertilizer drip irrigation liquid according to the fertilizer components and the water and fertilizer ratio, and drip irrigate the water and fertilizer drip irrigation liquid in the drip irrigation region according to the drip irrigation amount.

2. The intelligent drip irrigation method for a vegetable greenhouse as claimed in claim 1, wherein, When obtaining the growth information and environmental information of each vegetable crop in the vegetable greenhouse, the method comprises the following steps: Obtain the growth characteristic parameters of each vegetable crop, and determine the growth stage information of each vegetable crop according to the growth characteristic parameters, wherein the growth characteristic parameters include the plant height information, leaf area information, chlorophyll content information and canopy coverage information of the vegetable crop; Obtain the environmental parameters and soil parameters in the vegetable greenhouse, wherein the environmental parameters include the air temperature, air humidity, light parameters and carbon dioxide concentration in the vegetable greenhouse, and the soil parameters include the soil humidity, soil temperature, soil pH value, soil electrical conductivity and soil chemical component content.

3. The intelligent drip irrigation method for a vegetable greenhouse as claimed in claim 2, wherein, When identifying the regions of the vegetable greenhouse according to the growth information and environmental information to determine the drip irrigation region and the non-drip irrigation region, the method comprises the following steps: Standardize the obtained growth information and environmental information of the vegetable crop, and interpolate and fill in the missing data to construct a time-space continuous data set in the vegetable greenhouse; Divide the greenhouse region into multiple sub-regions based on the spatial clustering method according to the time-space continuous data set, wherein each sub-region has similar crop growth state and environmental characteristics; For each sub-region, determine the drip irrigation state of each sub-region according to the set soil humidity threshold, lower limit of chlorophyll content and historical water use response model, and determine the drip irrigation region and the non-drip irrigation region according to the drip irrigation state of each sub-region.

4. The intelligent drip irrigation method for a vegetable greenhouse as claimed in claim 3, wherein, When determining the drip irrigation state of each sub-region according to the set soil humidity threshold, lower limit of chlorophyll content and historical water use response model, the method comprises the following steps: Extract the soil humidity value, chlorophyll content value and historical water use response data of the sub-region according to the time-space continuous data set of the sub-region; Determine the humidity state value of the sub-region according to the relationship between the soil humidity value and the configured preset soil humidity value; Determine the nutrient state value of the sub-region according to the relationship between the chlorophyll content value and the configured preset lower limit of chlorophyll content; Determine the water shortage risk score of the sub-region by substituting the historical water use response data into the historical water use response model constructed based on the crop growth response; Determine the drip irrigation state of the sub-region according to the humidity state value, nutrient state value and water shortage risk score of the sub-region, wherein: Compare the humidity state value of the sub-region with the configured preset humidity state value, and determine the Boolean mark of the humidity state according to the comparison result; Comparing the nutrient status value of the sub-region with the configured preset nutrient status value, and determining the Boolean flag of the nutrient status according to the comparison result; Comparing the water shortage risk score of the sub-region with the configured preset water shortage risk score, and determining the Boolean flag of the water shortage risk according to the comparison result; Aggregating the Boolean flag of the humidity status, the Boolean flag of the nutrient status and the Boolean flag of the water shortage risk based on the configured AND logic rule; According to the aggregation result, determining the drip irrigation status of the sub-region, wherein the drip irrigation status includes no need for drip irrigation status, only water supplement drip irrigation status, only fertilizer application drip irrigation status, water and fertilizer integrated drip irrigation status and emergency drip irrigation status.

5. The intelligent drip irrigation method for a vegetable greenhouse as claimed in claim 4, wherein, When determining the drip irrigation region and the non-drip irrigation region according to the drip irrigation status of each sub-region, comprising: Obtaining the drip irrigation status of each sub-region, and determining the drip irrigation region and the non-drip irrigation region according to the drip irrigation status, wherein: If the drip irrigation status of the sub-region is the no need for drip irrigation status, then the sub-region is determined as the non-drip irrigation region; If the drip irrigation status of the sub-region is the only water supplement drip irrigation status, the only fertilizer application drip irrigation status, the water and fertilizer integrated drip irrigation status or the emergency drip irrigation status, then the sub-region is determined as the drip irrigation region.

6. The intelligent drip irrigation method for a vegetable greenhouse as claimed in claim 1, wherein, When determining the growth pathology of the vegetable crop in the drip irrigation region according to the growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategy, comprising: Obtaining the growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategy of each vegetable crop in the drip irrigation region, and performing normalization processing on the growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategy; According to the normalized growth characteristic parameters, the environmental information and the historical water and fertilizer drip irrigation strategy, determining the water shortage value, the nitrogen deficiency value, the phosphorus deficiency value, the potassium deficiency value and the salt stress score of the drip irrigation region; Determining the relationship between the water shortage value, the nitrogen deficiency value, the phosphorus deficiency value, the potassium deficiency value and the salt stress score of the drip irrigation region and the corresponding preset threshold value, and determining the pathological characteristics of the drip irrigation region; Matching the pathological characteristics with each preset pathological characteristic in the configured set of crop growth pathological characteristics, and determining the growth pathology of each vegetable crop in the drip irrigation region according to the matching result, wherein: Obtaining the feature similarity between the pathological characteristics and each preset pathological characteristic, arranging the feature similarities in reverse order, and determining the first corresponding preset pathological characteristic in the feature similarity arrangement as the pathological characteristics of the drip irrigation region.

7. The intelligent drip irrigation method for a vegetable greenhouse as claimed in claim 6, wherein, When configuring the set of crop growth pathological characteristics, comprising: Obtaining each growth pathology type of each vegetable crop, and the growth characteristic parameters, the environmental information and the soil water and fertilizer content corresponding to each growth pathology type; According to each growth pathology type of the vegetable and the growth characteristic parameters, the environmental information and the soil water and fertilizer content corresponding to each growth pathology type, establishing each growth pathology correlation formula of the vegetable; Obtaining the distance measure between each growth pathology correlation formula, and establishing a distance matrix according to the distance measure; Iteratively clustering each growth pathology correlation formula according to the distance matrix, and determining the pathological characteristic vector of each growth pathology type of the vegetable according to the clustering result; According to the pathological characteristic vector of each growth pathology type of each vegetable, establishing the set of crop growth pathological characteristics.

8. The intelligent drip irrigation method for a vegetable greenhouse as claimed in claim 1, wherein, The method comprises the following steps: Matching the growth pathology with a preset nutrient demand database to generate an initial fertilizer component demand; According to the environmental information, the crop transpiration and soil evaporation are obtained, and the initial fertilizer component demand is corrected; The corrected fertilizer component demand, crop transpiration, soil evaporation and soil water storage are used to determine a basic drip irrigation amount; According to the corrected fertilizer component demand and the basic drip irrigation amount, the fertilizer component and the drip irrigation amount for the drip irrigation of the region to be drip irrigated are determined.

9. The intelligent drip irrigation method for a vegetable greenhouse as claimed in claim 8, wherein, According to the chemical characteristic parameters of each component of the fertilizer and the drip irrigation amount, the water-fertilizer ratio is determined, which comprises the following steps: Based on the effective nutrient content of each component of the fertilizer, the drip irrigation amount and the target fertilization amount of the region to be drip irrigated, the target concentration of each nutrient in the drip irrigation liquid is determined; Based on the target concentration vector and the contribution parameters of the unit concentration of each component of the fertilizer to the EC and pH, the predicted EC value and pH value of the target solution are determined; According to the relationship between the target concentration vector, the predicted EC / pH and the solubility and compatibility parameters of the fertilizer, the water-fertilizer matching scheme is determined.

10. An intelligent drip irrigation system for a vegetable greenhouse, adapted to an intelligent drip irrigation method for a vegetable greenhouse according to any one of claims 1-9, characterized in that, The method comprises the following steps: The acquisition module is configured to obtain the growth information and environmental information of each vegetable crop in the vegetable greenhouse, and to identify the vegetable greenhouse according to the growth information and environmental information, to determine the drip irrigation region and the non-drip irrigation region; the acquisition module is also configured to obtain the growth characteristic parameters of each vegetable crop in the drip irrigation region and the historical water and fertilizer drip irrigation strategy; The analysis module is electrically connected with the acquisition module, and is configured to determine the growth pathology of the vegetable crop in the irrigation region according to the growth characteristic parameters and environmental information and the historical water and fertilizer drip irrigation strategy; The analysis module is also configured to determine the fertilizer component and the drip irrigation amount based on the growth pathology and the environmental information, and to determine the water-fertilizer ratio according to the chemical characteristic parameters of each component of the fertilizer and the drip irrigation amount; The control module is electrically connected with the analysis module, and is configured to prepare the water and fertilizer drip irrigation liquid according to the fertilizer component and the water-fertilizer ratio, and to drip irrigate the drip irrigation region with the water and fertilizer drip irrigation liquid according to the drip irrigation amount.

Images