Dynamic data fusion method and system for fruit and vegetable production facilities

Abstract

The invention relates to the technical field of crop cultivation, in particular to a dynamic data fusion method and system for a fruit and vegetable production facility, and the method comprises the steps: determining soil humidity data and crop images of all crop positions; determining an abnormal position in the crop position by using the soil humidity data, and determining the crop water absorption capacity of the abnormal position by using the crop image; determining the water demand degree of the crop at the abnormal position by using the soil humidity data and the water absorption capacity of the crop; and determining the target dripping rate of the abnormal position by using the crop water demand degree. According to the technical scheme, the water requirements of fruits and vegetables in different growth stages and different environments can be accurately mastered, so that the dripping speed of the drip irrigation system is accurately adjusted, and the soil humidity is more beneficial to growth of crops.

Description

Technical Field

[0001] The present invention relates to the technical field of crop cultivation, and particularly relates to a dynamic data fusion method and system for facilities in fruit and vegetable production facilities. Background Art

[0002] Fruit and vegetable production in facilities refers to an agricultural production method in which fruits and vegetables are planted in a greenhouse, a shed or other artificial environments by using control technologies. As a main facility planting environment, the shed provides a controllable growth environment for fruits and vegetables, which can avoid the influence of external weather, enabling crops to grow in a relatively stable environment, thereby increasing yield and quality. In shed planting, drip irrigation technology is often used to precisely irrigate fruits and vegetables. Through the pipeline system, water and nutrient solutions are directly dripped to the roots of plants, which can provide precise water management, avoiding water waste and excessive soil moisture.

[0003] Traditional drip irrigation systems usually control the dripping rate of drip heads by monitoring the soil humidity at the location of the crops. However, the actual water dripping amount is affected by the drip irrigation water pressure. Without considering the growth conditions of the crops, when adjusting the drip rate of the drip heads, the actual water demand of the crops is not taken into account, and these data are not effectively fused, resulting in the inability to accurately grasp the true needs of each crop, and thus unable to reasonably control the drip rate of the drip heads, leading to a soil humidity that is not conducive to the growth of the crops. Summary of the Invention

[0004] In order to solve the technical problem that the unreasonable control of the drip rate of drip heads during the drip irrigation process in fruit and vegetable production in facilities leads to a soil humidity that is not conducive to the growth of the crops, the purpose of the present invention is to provide a dynamic data fusion method and system for facilities in fruit and vegetable production facilities. The specific technical solutions adopted are as follows:

[0005] The present invention provides a dynamic data fusion method for facilities in fruit and vegetable production facilities, and the method includes:

[0006] Determine the soil humidity data and crop images at the positions of each crop;

[0007] Use the soil humidity data to determine the abnormal positions in the crop positions, and use the crop images to determine the water absorption capacity of the crops at the abnormal positions;

[0008] Use the soil humidity data and the water absorption capacity of the crops to determine the water demand degree of the crops at the abnormal positions;

[0009] Use the water demand degree of the crops to determine the target dripping rate at the abnormal positions.

[0010] Furthermore, the determining the abnormal positions in the crop positions by using the soil humidity data includes:

[0011] Determine the target humidity data of the target crop positions at each moment and the average humidity data of all crop positions;

[0012] Using the target humidity data and the average humidity data, calculate the humidity anomaly factor of the target crop positions;

[0013] Using the humidity anomaly factor, determine the abnormal positions among the crop positions.

[0014] Furthermore, the step of using the humidity anomaly factor to determine the abnormal positions among the crop positions includes:

[0015] Using the humidity anomaly factor to determine the humidity anomaly moments and the abnormal periods composed of consecutive humidity anomaly moments;

[0016] Using the water pressure time series data and the soil humidity time series data within the abnormal periods, determine the correlation degree between the soil humidity anomaly and the water pressure;

[0017] Compare the correlation degree with the preset correlation threshold to determine the abnormal positions among the crop positions.

[0018] Furthermore, the step of using the crop image to determine the crop water absorption capacity of the abnormal positions includes:

[0019] Using the crop image to determine the crop coverage area and the crop height of the abnormal positions;

[0020] Using the crop coverage area and the crop height, calculate the crop water absorption capacity.

[0021] Furthermore, the step of using the soil humidity data and the crop water absorption capacity to determine the crop water requirement degree of the abnormal positions includes:

[0022] Using the soil humidity data to determine the soil water shortage degree and the water shortage amount at each moment of the abnormal positions;

[0023] Using the soil water shortage degree and the water shortage amount, calculate the crop water shortage duration within the abnormal periods of the abnormal positions;

[0024] Using the crop water shortage duration and the crop water absorption capacity, calculate the crop water requirement degree of the abnormal positions.

[0025] Furthermore, the step of using the soil humidity data to determine the soil water shortage degree of the abnormal positions includes:

[0026] Using the soil humidity data to determine the humidity anomaly factor sequence within the abnormal periods of the abnormal positions;

[0027] Determine the water shortage anomaly quantity of the humidity anomaly factors less than the preset anomaly threshold in the humidity anomaly factor sequence;

[0028] Determine the soil water shortage degree at the abnormal position by using the proportion of the number of abnormal water shortages in the humidity anomaly factor sequence.

[0029] Furthermore, determine the water shortage amount at each moment at the abnormal position by using the soil humidity data, including:

[0030] Determine the unit humidity data at each moment at the abnormal position and the average humidity data at all moments;

[0031] Calculate the water shortage amount at each moment at the abnormal position by using the unit humidity data and the average humidity data.

[0032] Furthermore, the determination of the target drip rate at the abnormal position by using the crop water requirement degree includes:

[0033] Calculate the target drip rate at the abnormal position by using the crop water requirement degree and the soil humidity data at the abnormal position.

[0034] Furthermore, after determining the soil humidity data and the crop images at each crop position, it further includes:

[0035] Determine the crop water absorption capacity at the normal positions in the crop positions by using the crop images;

[0036] Determine the crop water requirement degree at the normal positions by using the crop water absorption capacity at the normal positions.

[0037] The present invention also provides a dynamic data fusion system for a facility fruit and vegetable production facility, and the system is used to implement the dynamic data fusion method for a facility fruit and vegetable production facility as described in any one of the above; the system includes:

[0038] A data acquisition module, used to determine the soil humidity data and the crop images at each crop position;

[0039] A water requirement analysis module, used to determine the abnormal positions in the crop positions by using the soil humidity data, determine the crop water absorption capacity at the abnormal positions by using the crop images; determine the crop water requirement degree at the abnormal positions by using the soil humidity data and the crop water absorption capacity;

[0040] A drip rate control module, used to determine the target drip rate at the abnormal position by using the crop water requirement degree.

[0041] The present invention has the following beneficial effects:

[0042] By monitoring the relationship between the soil humidity at each position in the greenhouse and the water flow rate of the drip irrigation, several humidity abnormal positions are determined, and the growth status of the crops at each position is obtained by using image processing technology to get the actual water demand degree of the crops at each position. By dynamically fusing and processing these data, the water demand of the fruit and vegetables at different growth stages and different environments can be accurately grasped, so as to precisely adjust the drip rate of the drip irrigation system, making the soil humidity more conducive to the growth of the crops. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the accompanying drawings required for use in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a flowchart of the steps of a dynamic data fusion method for a facility for fruit and vegetable production provided by an embodiment of the present invention;

[0045] Figure 2 It is a refined flowchart of step S2 in a dynamic data fusion method for a facility for fruit and vegetable production provided by an embodiment of the present invention;

[0046] Figure 3 It is a refined flowchart of step S23 in a dynamic data fusion method for a facility for fruit and vegetable production provided by an embodiment of the present invention;

[0047] Figure 4 It is a refined flowchart of step S3 in a dynamic data fusion method for a facility for fruit and vegetable production provided by an embodiment of the present invention;

[0048] Figure 5 It is a schematic structural diagram of the hardware operating environment of a dynamic data fusion device for a facility for fruit and vegetable production involved in the solution of the embodiment of the present invention;

[0049] Figure 6 It is a schematic framework diagram of a dynamic data fusion system for a facility for fruit and vegetable production involved in the solution of the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, a dynamic data fusion method for facility fruit and vegetable production facilities according to the present invention, including its specific implementation manner, structure, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0052] The following specifically describes the specific solution of a dynamic data fusion method for facility fruit and vegetable production facilities provided by the present invention in conjunction with the accompanying drawings.

[0053] Embodiment 1:

[0054] For the dynamic data fusion method for facility fruit and vegetable production facilities provided by the present invention, please refer to Figure 1 , which shows the flowchart of the steps of the dynamic data fusion method for facility fruit and vegetable production facilities provided by one embodiment of the present invention.

[0055] The method includes:

[0056] Step S1, determining the soil humidity data and crop images at each crop position.

[0057] First, for this embodiment, the specific scenario targeted can be:

[0058] In the same greenhouse, due to factors such as light and soil fertility, the growth conditions of crops at different crop positions (hereinafter referred to as positions) may also vary. And crops have different water requirements at different growth stages, and the root systems have different water absorption capabilities. Therefore, during drip irrigation, not only the soil humidity needs to be considered, but also the actual growth conditions of the crops at each position. In addition, facility fruits and vegetables are often in a relatively closed state, with high temperature and humidity in the shed, high evaporation, and lack of rain leaching effect.

[0059] In this embodiment, a capacitive humidity sensor can be used to obtain the soil humidity data. A capacitive humidity sensor usually consists of two metal electrodes and a capacitance measurement circuit, and a capacitance is formed between the electrodes through the soil. The measurement circuit determines the soil humidity by analyzing the change in the capacitance between the electrodes.

[0060] In the greenhouse, humidity sensors can be arranged at fixed intervals (such as one sensor every 5 - 10 meters) to ensure the humidity changes within the monitored area. The humidity sensors are installed in the root growth area of the crops, and the installation depth can be about 20 cm, so as to more clearly reflect the actual water requirements of the crops. The positions of the areas within a certain range of each humidity sensor (the detection coverage range of the humidity sensor can be set and adjusted according to needs) are the positions of each crop.

[0061] For the acquisition method of crop images in the greenhouse: Several high - definition cameras can be evenly arranged above the greenhouse. The height is set to be able to capture a sufficient area of the crop area, and the angle is adjusted to be vertically downward or slightly inclined at a certain angle to fully cover the crops and avoid capturing too much ground background, ensuring that the overall shape and leaf details of the crops can be clearly captured.

[0062] In addition, for the drip irrigation system of greenhouse crops, it consists of pipelines, filters, controllers, pressure pumps, etc. The pipelines are laid in the orchard, and a filter is installed at a certain distance. The pressure pump sends water to the pipelines, and the water drips into the roots of the crops through the drip heads. The drip irrigation system can automatically control the water supply, supply an appropriate amount of water according to the growth needs of the crops, avoid problems such as over - watering and drought, thereby improving the yield and quality of the crops.

[0063] Water pressure sensors can be installed at key positions of the drip irrigation system. Usually installed in the main pipeline, branch pipelines or near the drip heads. Through these sensors, the water pressure at different crop positions can be monitored in real time.

[0064] Step S2, determine the abnormal positions in the crop positions using the soil humidity data, and determine the water absorption capacity of the crops at the abnormal positions using the crop images.

[0065] Specifically, in one embodiment, please refer to Figure 2 , the step S2 includes:

[0066] Step S21, determine the target humidity data of the target crop positions at each moment and the average humidity data of all crop positions;

[0067] Step S22, use the target humidity data and the average humidity data to calculate the humidity anomaly factor of the target crop positions;

[0068] The soil humidity in the greenhouse is often non - uniform, and the soil humidity at different crop positions will be affected by factors such as the amount of drip irrigation water, ventilation, and lighting.

[0069] According to the soil humidity data S at the q - th position (target crop position) at the i - th moment q,i(Target humidity data) and the mean value of soil humidity data at all positions except or including the q-th position at the i-th moment (Average humidity data) to obtain the humidity anomaly factor B at the q-th position at the i-th moment q,i :

[0070]

[0071] where Th() is the hyperbolic tangent function, mapping B q,i to the interval [-1, 1].

[0072] Step S23, using the humidity anomaly factor to determine the abnormal positions in the crop positions.

[0073] Please refer to Figure 3 , the said step S23 includes:

[0074] Step S231, using the humidity anomaly factor to determine the humidity anomaly moments and the abnormal periods composed of consecutive humidity anomaly moments;

[0075] Step S232, using the water pressure time series data and soil humidity time series data within the abnormal period to determine the correlation degree between soil humidity anomaly and water pressure;

[0076] Step S233, comparing the correlation degree with the preset correlation threshold to determine the abnormal positions in the crop positions.

[0077] The water flow rate of the dripper is proportional to the water pressure in the water pipe. The higher the water pressure, the greater the water flow rate of the dripper, and the drip rate will also increase accordingly. Due to certain frictional losses in the pipes, connectors, valves, etc. of the drip irrigation system, the water pressure may vary at different positions in the greenhouse. Especially in places far from the water source, the water pressure will drop, resulting in a decrease in the drip water volume of the drippers at these positions and causing uneven soil humidity.

[0078] In the time series of soil humidity data at the q-th position, B q,i The moments when it is less than the first preset anomaly threshold (e.g., -0.7) or greater than the second preset anomaly threshold (e.g., 0.7) can be recorded as (suspected) humidity anomaly moments, and consecutive adjacent humidity anomaly moments form an abnormal period, obtaining multiple abnormal periods. If the current moment is within an abnormal period, continue to analyze the abnormal period where the current moment is located. If the current moment is not within an abnormal period, analysis may not be required.

[0079] Use the water pressure time series data of the water pressure sensor closest to the q-th position as the water pressure time series data of the q-th position for analysis.

[0080] Denote the abnormal period at the current moment as the y-th abnormal period. Then, in the y-th abnormal period, obtain the Pearson correlation coefficient R between the water pressure time series data and the soil humidity time series data at the q-th position in the y-th abnormal period. q,y 。

[0081] Since water flows continuously in the pipeline and adjacent areas are on the same pipeline branch as the q-th position, when the water pressure at the q-th position is abnormal, the adjacent areas will also be similarly affected, resulting in abnormal soil humidity in the adjacent areas.

[0082] In the y-th suspected abnormal period, according to the humidity anomaly factor B at the adjacent positions of the q-th position at each moment q-1,i 、B q+1,i , obtain the mean value of the anomaly factors of all adjacent positions of the q-th position at each moment.

[0083] Calculate the correlation degree G between the soil humidity anomaly and the water pressure at the q-th position in any y-th abnormal period q,y :

[0084]

[0085] Among them, is the sum value of the mean values of the anomaly factors of all adjacent positions of the q-th position at all moments in any y-th abnormal period . The greater the correlation degree, the more likely the abnormal degree of the soil humidity at the q-th position is related to the water pressure.

[0086] Denote the positions where G q,y is less than or equal to the preset correlation threshold (which can be 0.5) as abnormal positions. It can be considered that the abnormal soil humidity at these positions has nothing to do with the water pressure magnitude, and the reasons for the abnormal soil humidity need to be further analyzed.

[0087] Specifically, in another embodiment, the step S2 includes:

[0088] Use the crop image to determine the crop coverage area and crop height at the abnormal position;

[0089] Use the crop coverage area and crop height to calculate the crop water absorption capacity.

[0090] The above embodiments analyze whether the abnormal soil humidity at each position is affected by the water pressure of the drip irrigation pipe. However, during the operation of the greenhouse drip irrigation system, after the drippers slowly drip water into the soil, the water will diffuse in the soil pores. And the roots and stems of the crops are distributed in the soil and will continuously absorb water, which will also affect the soil humidity at each position. Therefore, it is necessary to further analyze the influence of the water absorption of the crop roots and stems on the soil humidity.

[0091] Since the growth condition of crops directly affects the development of their roots and rhizomes as well as their water absorption capacity, in the case of good growth, the root systems of crops are well-developed and the water absorption capacity is strong, which will lead to a decrease in the soil humidity around. On the contrary, if the growth state of crops is poor and the root development is bad, then their water absorption capacity is weak, and the water in the soil will remain at a high level. Therefore, first obtain the water absorption capacity of crops at each position by the growth condition of crops at each position in the greenhouse.

[0092] Establish a greenhouse coordinate system: Take the lower left corner of the greenhouse as the origin of the coordinate system, the long side direction as the x-axis, and the short side direction as the y-axis. Since all crop positions in the greenhouse are fixed and regularly arranged, map the image obtained by the image sensor to this coordinate system (determine the actual coordinates corresponding to each pixel point in the image through the installation position and angle of the image sensor).

[0093] For crops with good growth states, the metabolism is relatively vigorous and usually requires more water to maintain life activities. Therefore, the better the growth state of crops, the more developed the root systems of crops will be, and the wider the distribution range will be. They can absorb water from the soil in a larger area and have a stronger water absorption capacity for the soil.

[0094] Taking any x-th abnormal position as an example for analysis, use the image segmentation algorithm to segment the crops at the x-th abnormal position from the background. According to the coverage area s x and the crop height h x (which can be converted proportionally through the preset reference object in the image), obtain the water absorption capacity Z of the crops at the x-th abnormal position x :

[0095] Z x = s x × h x

[0096] Among them, the larger the coverage area of the crops and the higher the height, the better the growth state of the crops and the stronger the water absorption capacity. Similarly, the water absorption capacity of crops at each normal position can also be obtained.

[0097] Step S3, use the soil humidity data and the crop water absorption capacity to determine the water requirement degree of the crops at the abnormal position.

[0098] Specifically, in an embodiment, please refer to Figure 4 , the step S3 includes:

[0099] Step S31, use the soil humidity data to determine the soil water shortage degree and the water shortage amount at each moment at the abnormal position;

[0100] Specifically, determining the degree of soil water shortage at the abnormal location using soil moisture data includes:

[0101] Determining a sequence of humidity anomaly factors at the abnormal location during the abnormal period using soil moisture data;

[0102] Determining the number of water shortage anomalies of humidity anomaly factors less than a preset anomaly threshold in the sequence of humidity anomaly factors;

[0103] Determining the degree of soil water shortage at the abnormal location using the proportion of the number of water shortage anomalies in the sequence of humidity anomaly factors.

[0104] Since the environmental conditions in the greenhouse change with time and weather. For example, when the temperature is higher during the day, the transpiration of crops will increase, resulting in faster evaporation of water in the soil; while when the temperature is lower at night, the transpiration weakens and the water evaporation rate decreases. The growth state of crops and the water absorption capacity of roots also change with seasons and growth stages. Therefore, by fusing crop water absorption capacity data, the drip irrigation system can adjust the drip rate according to actual needs.

[0105] In the abnormal period where the current moment is located, based on the soil moisture data, the humidity anomaly factor B of the x-th abnormal location at all moments x,i constitutes a sequence of humidity anomaly factors, and the humidity anomaly factors from -1 to -0.7 can be set to -1, and those from 0.7 to 1 can be set to 1. For example, the sequence of humidity anomaly factors is {-1, -1, -1, 1, -1, 1}. Here, the preset anomaly threshold can be -0.7.

[0106] According to the number of moments N x,i when the humidity anomaly factor B in the sequence of humidity anomaly factors of the x-th abnormal location in the abnormal period where the current moment is located is -1 t,x,-1 (the number of water shortage anomalies) in the total number N of all moments in the sequence of humidity anomaly factors in the abnormal period where the current moment is located t,x the proportion, obtaining the degree of soil water shortage C of the x-th abnormal location in the abnormal period where the current moment is located t,x :

[0107]

[0108] C t,x The larger it is, the longer the x-th abnormal location is in a water shortage state and the higher the demand for water.

[0109] Specifically, determining the water shortage amount at the abnormal location at each moment using soil moisture data includes:

[0110] Determining the unit humidity data at the abnormal location at each moment and the average humidity data of all moments;

[0111] Using the unit humidity data and the average humidity data, calculate the water shortage amount at the abnormal position at each moment.

[0112] In the abnormal period where the current moment is located, for each humidity abnormal factor B x,i at the moment n with a value of -1, calculate the humidity data S x,i (unit humidity data) of the x-th abnormal position at any n-th moment (the moment when the n-th humidity abnormal factor B t,x,n,-1 has a value of -1), and the absolute value of the difference between the average value of the humidity data at all moments in the abnormal period where the current moment is located (average humidity data), to obtain the water shortage amount ΔS at the n-th moment in the period where the current moment is located t,x,n,-1 :

[0113]

[0114] Step S32: Using the soil water shortage degree and the water shortage amount, calculate the crop water shortage duration at the abnormal position during the abnormal period;

[0115] Step S33: Using the crop water shortage duration and the crop water absorption capacity, calculate the crop water demand degree at the abnormal position.

[0116] The time interval Δt between the n-th moment of the x-th abnormal position and the current moment t,x,n can also be used as the weight of the water shortage amount ΔS at the n-th moment, and calculate the crop water shortage duration T' t,x,n,-1 of the period where the current moment is located: t,x :

[0117]

[0118] where C t,x represents the soil water shortage degree, N t,x,-1 represents the number of water shortage abnormalities, ΔS t,x,n,-1 represents the water shortage amount, and Δt t,x,n represents the time interval. The smaller Δt t,x,n is, the closer the n-th moment is to the current moment. Here, the case where the n-th moment is the current moment is not analyzed. The water shortage amount ΔS t,x,n,-1 is more important, and is more important for the crop water shortage duration T' t,x and requires more attention.

[0119] Calculate the water demand degree X of the crop at the x-th abnormal position at the current moment t,x :

[0120] X t,x = 1 + norm(Z t,x × T' t,x)

[0121] Among them, T′ t,x represents the duration of water shortage of the crop, and Z t,x represents the water absorption capacity of the crop at the x-th abnormal position. norm represents the normalization calculation. The larger T′ t,x is, the more water is lost from the soil at the x-th abnormal position, and the less water the crop absorbs. To maintain life activities, the crop's demand for dripping water will be higher.

[0122] Step S4: Determine the target dripping rate at the abnormal position based on the water demand degree of the crop.

[0123] Specifically, step S4 includes:

[0124] Calculate the target dripping rate at the abnormal position by using the water demand degree of the crop and the soil humidity data at the abnormal position.

[0125] First, the dripping rate coefficient v at any position (including the abnormal position) at the current moment can be determined first t,m :

[0126]

[0127] V = v t,m ×V0

[0128] where M is the number of positions in the greenhouse, and X t,m represents the water demand degree of the crop at the m-th position at the current moment. The larger X t,m is, the more vigorously the crop grows at that position, the stronger the water absorption ability of the root system, and the more the soil humidity needs to be increased. S t,m represents the soil humidity data at the m-th position at the current moment. The smaller S t,m is, the drier the soil at that position, and the insufficient water available for the crop to absorb. The dripping rate needs to be increased to supplement water in a timely manner. However, generally, the soil humidity data S in the normal crop growth environment t,m has no possibility of being zero. For X t,m and S t,m They can be unified in dimension, scale, and distribution through normalization methods such as decimal scaling normalization, and then participate in the above calculation process after normalization. V0 represents the initial dripping rate at the abnormal position at the current moment, and V represents the target dripping rate at the abnormal position at the current moment.

[0129] After obtaining the dripping rate coefficient v t,m , the initial dripping rate can be corrected to obtain the target dripping rate. The larger this dripping rate coefficient is, the larger the corresponding target dripping rate is.

[0130] Input the target drip rate V at the current moment into the PID controller, and output a drip rate control instruction for the next moment at the current moment. The drip rate control instruction will be transmitted to each drip head control component in the drip irrigation system through a signal transmission line.

[0131] After each drip head control component receives the control instruction, it will adjust the opening degree or working state of the drip head according to the instruction. For example, for an electromagnetic valve, the cross-sectional area of the water flow is controlled by changing the opening degree of the valve, thereby adjusting the drip rate of the drip head; for a drip head device driven by a speed control motor, the motor adjusts the speed according to the instruction, and then changes the water output and drip rate of the drip head.

[0132] In addition, for the normal position in the crop position, in one embodiment, after the step S1, the method further includes:

[0133] Determine the water absorption capacity of the crops in the normal position in the crop position by using the crop image;

[0134] Determine the water requirement degree of the crops in the normal position by using the water absorption capacity of the crops in the normal position.

[0135] Referring to the above embodiment, this embodiment can be expressed as:

[0136] X t,m = 1 + norm(Z t,m )

[0137] Wherein, X t,m represents the water requirement degree of the crops in the normal position, and Z t,m represents the water absorption capacity of the crops in the normal position.

[0138] That is, set the water requirement degree of each crop in the normal position at the current moment to the normalized value of the water absorption capacity of the crop in the normal position at the current moment.

[0139] By monitoring the relationship between the soil humidity and the drip water flow rate at each position in the greenhouse, the present invention determines several humidity abnormal positions, and uses image processing technology to obtain the growth status of the crops at each position, obtains the actual water requirement degree of the crops at each position, and performs dynamic fusion processing on these data, so as to accurately grasp the water requirements of fruit and vegetables at different growth stages and different environments, thereby accurately adjusting the drip rate of the drip irrigation system, making the soil humidity more conducive to the growth of the crops.

[0140] Embodiment 2:

[0141] The embodiment of the present invention also proposes a dynamic data fusion device for a facility fruit and vegetable production facility. The dynamic data fusion device for a facility fruit and vegetable production facility can be a programmable logic controller, a computer, a server and other data calculation and processing devices or a combination of multiple devices.

[0142] As shown Figure 5 in Figure 5 FIG. 1, it is a schematic structural diagram of the hardware operating environment of a dynamic data fusion device for a facility fruit and vegetable production facility according to an embodiment of the present invention.

[0143] As shown Figure 5 in FIG. 2, the dynamic data fusion device for the facility fruit and vegetable production facility may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display (Display) and an input unit such as a control panel. Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WIFI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001. The memory 1005, as a computer storage medium, may include a dynamic data fusion program for the facility fruit and vegetable production facility.

[0144] Those skilled in the art can understand that Figure 5 the hardware structure shown in FIG. 3 does not constitute a limitation on the device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0145] Continuing to refer to Figure 5 , Figure 5 the memory 1005, as a computer-readable storage medium, may include an operating system, a user interface module, a network communication module, and a dynamic data fusion program for the facility fruit and vegetable production facility.

[0146] In Figure 5 FIG. 4, the network communication module is mainly used to connect to the server and can communicate with the server; and the processor 1001 can call the dynamic data fusion program stored in the memory 1005 and execute the steps in the above respective embodiments.

[0147] Based on the above hardware structure of the dynamic data fusion device for the facility fruit and vegetable production facility, various embodiments for implementing the dynamic data fusion method for the facility fruit and vegetable production facility of the present invention are realized.

[0148] In addition, the present invention further provides a dynamic data fusion system for a facility fruit and vegetable production facility. Please refer to Figure 6, the dynamic data fusion system for facility fruit and vegetable production facilities includes:

[0149] Data acquisition module A10, used to determine the soil humidity data and crop images at each crop position;

[0150] Water requirement analysis module A20, used to determine the abnormal positions in the crop positions by using the soil humidity data, determine the crop water absorption capacity of the abnormal positions by using the crop images; determine the crop water requirement degree of the abnormal positions by using the soil humidity data and the crop water absorption capacity;

[0151] Drip rate control module A30, used to determine the target drip rate of the abnormal positions by using the crop water requirement degree.

[0152] Furthermore, the water requirement analysis module A20 is also used for:

[0153] Determine the target humidity data of the target crop positions and the average humidity data of all crop positions at each moment;

[0154] Calculate the humidity anomaly factor of the target crop positions by using the target humidity data and the average humidity data;

[0155] Determine the abnormal positions in the crop positions by using the humidity anomaly factor.

[0156] Furthermore, the water requirement analysis module A20 is also used for:

[0157] Determine the humidity anomaly moments and the abnormal time periods composed of consecutive humidity anomaly moments by using the humidity anomaly factor;

[0158] Determine the correlation degree between the soil humidity anomaly and the water pressure by using the water pressure time series data and the soil humidity time series data within the abnormal time period;

[0159] Compare the correlation degree with the preset correlation threshold to determine the abnormal positions in the crop positions.

[0160] Furthermore, it is necessary to determine the crop coverage area and crop height of the abnormal positions by using the crop images;

[0161] Calculate the crop water absorption capacity by using the crop coverage area and the crop height. The water analysis module A20 is also used for:

[0162] Furthermore, the water requirement analysis module A20 is also used for:

[0163] Determine the soil water shortage degree and the water shortage amount at each moment of the abnormal positions by using the soil humidity data;

[0164] Calculate the crop water shortage duration of the abnormal positions within the abnormal time period by using the soil water shortage degree and the water shortage amount;

[0165] Based on the water shortage duration of the crop and the water absorption capacity of the crop, the water requirement degree of the abnormal position is calculated.

[0166] Furthermore, the water requirement analysis module A20 is further configured to:

[0167] Determine the humidity anomaly factor sequence of the abnormal position during the abnormal period by using the soil humidity data;

[0168] Determine the number of water shortage anomalies of the humidity anomaly factors less than the preset anomaly threshold in the humidity anomaly factor sequence;

[0169] Determine the soil water shortage degree of the abnormal position by using the proportion of the number of water shortage anomalies in the humidity anomaly factor sequence.

[0170] Furthermore, the water requirement analysis module A20 is further configured to:

[0171] Determine the unit humidity data of the abnormal position at each moment and the average humidity data of all moments;

[0172] Calculate the water shortage amount of the abnormal position at each moment by using the unit humidity data and the average humidity data.

[0173] Furthermore, the drip rate control module A30 is further configured to:

[0174] Calculate the target drip rate of the abnormal position by using the water requirement degree of the crop at the abnormal position and the soil humidity data.

[0175] Furthermore, the water requirement analysis module A20 is further configured to:

[0176] Determine the water absorption capacity of the crops at the normal positions in the crop positions by using the crop images;

[0177] Determine the water requirement degree of the crops at the normal positions by using the water absorption capacity of the crops at the normal positions.

[0178] The specific implementation manners of the dynamic data fusion system for facility fruit and vegetable production facilities of the present invention are basically the same as those of the above embodiments of the dynamic data fusion method for facility fruit and vegetable production facilities, and will not be elaborated herein.

[0179] In addition, the present invention also provides a computer-readable storage medium. A dynamic data fusion program for facility fruit and vegetable production facilities is stored on the computer-readable storage medium of the present invention. When the dynamic data fusion program for facility fruit and vegetable production facilities is executed by a processor, the steps of the above-mentioned dynamic data fusion method for facility fruit and vegetable production facilities are implemented.

[0180] Among them, the method implemented when the dynamic data fusion program for the facility fruit and vegetable production facility is executed can refer to each embodiment of the dynamic data fusion method for the facility fruit and vegetable production facility of the present invention, which will not be elaborated here.

[0181] It should be noted that the above-mentioned order of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0182] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized.

[0183] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0184] The above are only the preferred embodiments of the present invention, and do not limit the protection scope of the present invention. Any equivalent structure / method transformation made by using the specification and drawings of the present invention under the inventive concept of the present invention, or direct / indirect application in other related technical fields, is included in the protection scope of the present invention.

Claims

1. A dynamic data fusion method for facility fruit and vegetable production facilities, characterized in that, The method includes: Determining soil moisture data and crop images at each crop position; Using the soil moisture data to determine abnormal positions among the crop positions, and using the crop images to determine the crop water absorption capacity at the abnormal positions; Using the soil moisture data and the crop water absorption capacity to determine the crop water requirement degree at the abnormal positions; Using the crop water requirement degree to determine the target drip rate at the abnormal positions.

2. The dynamic data fusion method for facility fruit and vegetable production facilities according to claim 1, characterized in that The determining abnormal positions among the crop positions using the soil moisture data includes: Determining the target moisture data at the target crop positions and the average moisture data at all crop positions at each moment; Using the target moisture data and the average moisture data to calculate the moisture anomaly factor at the target crop positions; Using the moisture anomaly factor to determine the abnormal positions among the crop positions.

3. The dynamic data fusion method for facility fruit and vegetable production facilities according to claim 2, wherein The determining abnormal positions among the crop positions using the moisture anomaly factor includes: Using the moisture anomaly factor to determine the moisture anomaly moments and the abnormal periods composed of consecutive moisture anomaly moments; Using the water pressure time series data and the soil moisture time series data within the abnormal periods to determine the correlation degree between the soil moisture anomaly and the water pressure; Comparing the correlation degree with a preset correlation threshold to determine the abnormal positions among the crop positions.

4. The dynamic data fusion method for a facility for fruit and vegetable production according to claim 1, wherein The determining the crop water absorption capacity at the abnormal positions using the crop images includes: Using the crop images to determine the crop coverage area and the crop height at the abnormal positions; Using the crop coverage area and the crop height to calculate the crop water absorption capacity.

5. The dynamic data fusion method for facility fruit and vegetable production facilities according to claim 1, wherein The determining the crop water requirement degree at the abnormal positions using the soil moisture data and the crop water absorption capacity includes: Using the soil moisture data to determine the soil water shortage degree and the water shortage amount at each moment at the abnormal positions; Using the soil water shortage degree and the water shortage amount to calculate the crop water shortage duration within the abnormal periods at the abnormal positions; Using the crop water shortage duration and the crop water absorption capacity to calculate the crop water requirement degree at the abnormal positions.

6. The dynamic data fusion method for facility fruit and vegetable production facilities according to claim 5, characterized in that, The determining the soil water shortage degree at the abnormal positions using the soil moisture data includes: Using the soil moisture data to determine the sequence of moisture anomaly factors within the abnormal periods at the abnormal positions; Determining the water shortage anomaly quantity of the moisture anomaly factors less than a preset anomaly threshold in the sequence of moisture anomaly factors; Using the proportion of the water shortage anomaly quantity in the sequence of moisture anomaly factors to determine the soil water shortage degree at the abnormal positions.

7. The dynamic data fusion method for facility fruit and vegetable production facilities according to claim 6, characterized in that The determining the water shortage amount at each moment at the abnormal positions using the soil moisture data includes: Determining the unit moisture data at each moment at the abnormal positions and the average moisture data at all moments; Using the unit moisture data and the average moisture data to calculate the water shortage amount at each moment at the abnormal positions.

8. The dynamic data fusion method for facility fruit and vegetable production facilities according to claim 1, characterized in that The determining the target drip rate at the abnormal positions using the crop water requirement degree includes: Using the crop water requirement degree and the soil moisture data at the abnormal positions to calculate the target drip rate at the abnormal positions.

9. The dynamic data fusion method for facility fruit and vegetable production facilities according to claim 1, characterized in that After the determining the soil moisture data and the crop images at each crop position, it further includes: Using the crop images to determine the crop water absorption capacity at the normal positions among the crop positions; Using the crop water absorption capacity at the normal positions to determine the crop water requirement degree at the normal positions.

10. A dynamic data fusion system for a facility for fruit and vegetable production, characterized in that, The system is used to implement the dynamic data fusion method for facility fruit and vegetable production facilities as described in any one of claims 1 to 9; the system includes: A data acquisition module for determining soil moisture data and crop images at the positions of various crops; A water requirement analysis module for determining abnormal positions in the crop positions using the soil moisture data, determining the water absorption capacity of the crops at the abnormal positions using the crop images; and determining the water requirement degree of the crops at the abnormal positions using the soil moisture data and the water absorption capacity of the crops; A drip rate control module for determining the target drip rate at the abnormal positions using the water requirement degree of the crops.

Images