An automatic monitoring system for solution ion content based on the Internet of Things

Abstract

The present application relates to the technical field of solution detection, and in particular to a solution ion content automatic monitoring system based on the Internet of Things, comprising: a camera module for collecting plant image data of cultivated plants in a plant factory; a selection module for traversing the plant image data collected by the camera module and selecting a local area in the plant image data as a monitoring target area for this system run; a sampling module for receiving the monitoring target area selected by the selection module and sampling the solution of the cultivated plants in the monitoring target area; the present application analyzes the growth of the cultivated plants by image collection of the cultivated plants, selects two positions with the best and worst growth states as the nutrient solution sampling positions, samples the nutrient solution, further analyzes the health state of the nutrient solution based on the set nutrient solution monitoring state analysis logic, and monitors the safety of the nutrient solution used for the cultivated plants according to the continuously analyzed nutrient solution health state.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of solution detection, in particular to a solution ion content automatic monitoring system based on Internet of Things. BACKGROUND

[0002] Plant factory is an innovative achievement of modern agriculture, which is a highly controllable agricultural production mode. It provides the best growth environment for plants by artificially controlling light, temperature, humidity, nutrition and other growth conditions in a completely closed environment. Nutrient solution culture is a kind of cultivation technology for cultivating plants in plant factory.

[0003] The invention patent with application number 201710099997.4 discloses a plant hydroponic nutrient solution component detection method, which is characterized by the following steps: step S10 initial data input and detection: the ion detection module detects the ion concentration of the hydroponic nutrient solution through the sensor, and defines the ion concentration data as the initial concentration; step S20 nutrient analysis: the biological species analysis module calls the data in the tissue culture management module, analyzes the influence of the current plant species on the nutrient components of the nutrient solution in the corresponding hydroponic stage according to the hydroponic stage and the plant species combined with the data in the local database; step S30 real-time ion concentration detection: the ion detection module continuously detects the ion concentration of the hydroponic nutrient solution through the sensor, and defines it as the real-time ion concentration; step S40 nutrient solution nutrient change trend calculation: the nutrient analysis module calls the ion concentration data of the nutrient solution formula, and calculates the real-time standard ion concentration according to the analysis result of step S20; step S50 ion component comparison: the central processor compares the real-time ion concentration obtained in step S30 with the real-time standard ion concentration obtained in step S40, and sends a reminder to replace the nutrient solution when the comparison result is inconsistent; step S60 nutrient component monitoring: the central processor monitors the real-time ion concentration obtained in step S30, and sends a reminder to replace the nutrient solution when the real-time ion concentration is lower than the set alarm value.

[0004] The application aims to solve the problem that "due to the lack of detection method for nutrient components of nutrient solution, all plants are replaced with nutrient solution at a fixed time, which leads to the environment of nutrient deficiency for some plants with large consumption, and waste of plants with slow consumption".

[0005] However, for large-area nutrient solution cultivation of plants, there are differences in plant growth, and the absorption capacity of nutrient solution cannot be balanced. Due to the large area of nutrient solution cultivation of plants, it is impossible to accurately monitor the state of nutrient solution components, so it is impossible to provide the best growth environment for plants;

[0006] Therefore, we propose a solution ion content automatic monitoring system based on Internet of Things. SUMMARY

[0007] In view of the above-mentioned defects of the prior art, the present application provides a solution ion content automatic monitoring system based on Internet of Things, which solves the technical problems proposed in the above background art.

[0008] To achieve the above object, the present application is implemented by the following technical solutions:

[0009] A solution ion content automatic monitoring system based on Internet of Things, comprising:

[0010] A camera module is used to collect plant image data in a plant factory; a selection module is used to traverse the plant image data collected by the camera module and select a local area in the plant image data as a monitoring target area for this system run; a sampling module is used to receive the monitoring target area selected by the selection module and sample the solution of the cultivated plants in the monitoring target area; a sensing module is used to receive the sampled solution in the sampling module and synchronously sense the state parameters of each group of solutions; an analysis module is used to record the sampled solution state parameters sensed by the sensing module in real time, analyze the nutrient solution health state based on the sampled solution state parameters; and a monitoring module is used to set a nutrient solution state health determination threshold, continuously receive the nutrient solution health state analyzed by the analysis module, and monitor the safety of the nutrient solution based on the nutrient solution state health determination threshold and the nutrient solution health state analysis result.

[0011] The camera module is internally connected to a segmentation unit through a wireless network interaction, the camera module and the segmentation unit are connected to a selection module through a wireless network interaction, the selection module is connected to a sampling module through a wireless network interaction, the sampling module is connected to a mechanical arm module and a sampling pump through a medium electrical connection at a lower level, and the sampling module is connected to a sensing module, an analysis module and a monitoring module through a wireless network interaction.

[0012] Further, the camera module is arranged directly above the cultivated plants in the plant factory, the camera module has a vertical downward camera end, and the camera module has a system end user-defined running period, and the camera module continuously collects plant image data based on the running period.

[0013] The plants cultivated in the plant factory are nutrient solution cultivation, the plants arranged in the plant factory are arranged in a matrix, the cultivated plant varieties arranged in the matrix are consistent, and the nutrient solution is consistent.

[0014] Further, the image edges of the plant image data collected by the camera module coincide with the boundaries of the cultivated plants arranged in a matrix, and the camera module is internally provided with a sub-module, comprising:

[0015] A segmentation unit is used to receive the plant image data collected by the camera module and perform segmentation processing on the plant image data.

[0016] The plant image data segmentation logic is set in the segmentation unit, the plant image data is segmented based on the plant image data segmentation logic in the segmentation unit, each image block obtained by the segmentation is recorded as sub-plant image data, the number of each sub-plant image data is not less than 2*2 groups, and the size and the aspect ratio of each sub-plant image data are equal.

[0017] Further, the plant image data segmentation logic set in the processing unit is represented as:

[0018]

[0019] In the formula, m is the total amount of the sub-plant image data after the segmentation; q is the image segmentation base; f(i,j) is the frequency of the feature binary tuple (i,j); n is the scale of the image; and λ is the correction.

[0020] In the formula, the correction λ≥1, and is subject to The greater the correction λ is, the greater the value of the correction λ is, and vice versa. The value of the image segmentation base q is 2*2 groups, the total amount m of the sub-plant image data after the segmentation is rounded up, and The value of i is a gray value of a pixel, and the value of j is a field gray mean value.

[0021] Further, the selection operation of the local area in the plant image data, that is, the selection operation of the sub-plant image data, is performed in the selection module. In the running stage of the selection module, the information entropy of each sub-plant image data is calculated, two groups of sub-plant image data are further selected, and the two groups of selected sub-plant image data are the sub-plant image data with the maximum and minimum information entropy.

[0022] In the formula, the information entropy calculation logic of the sub-plant image data is

[0023] Further, the sampling module is provided with a sub-module, including:

[0024] The mechanical arm module is used for carrying the sampling pump to move above the matrix-distributed cultivated plants, to reach the center position of the cultivated plant area corresponding to the monitoring target area, and to vertically push the sampling pump to extend into the nutrient solution of the cultivated plant;

[0025] The sampling pump is used for continuously performing three times of nutrient solution sample collection at the center position of the cultivated plant area corresponding to the monitoring target area in a state that the pump suction end of the sampling pump extends into the nutrient solution.

[0026] Among them, the robotic arm module pushes the sampling pump into the nutrient solution for growing plants, so that the sampling pump reaches the bottom of the nutrient solution at a uniform speed. Each time the sampling pump penetrates one-third of the depth of the nutrient solution, a nutrient solution sub-sample is collected. Three groups of nutrient solution sub-samples collected at the center position of the plant cultivation area corresponding to the same monitoring target area are mixed and recorded as a group of nutrient solution samples to be tested.

[0027] Furthermore, the sensing module is integrated with a conductivity sensor and a microelectrode array sensor, and the sensing module operates to receive the sample solution in the sampling module, i.e., the nutrient solution sample to be tested;

[0028] The state parameters of the nutrient solution sample to be tested sensed by the sensing module include: ion content, ammonia ion content, phosphorus ion content, potassium ion content, chloride ion content, and nitrite ion content in the nutrient solution.

[0029] Furthermore, the health status analysis logic of the nutrient solution in the analysis module is expressed as:

[0030]

[0031] Where: F is the health status performance value of the nutrient solution presented by the state parameters of a group of nutrient solution samples to be tested; ρ NH , ρ HPO , ρ K , ρ CL , ρ NO is the content of ammonia ion, phosphorus ion, potassium ion, chloride ion and nitrite ion in the nutrient solution; ρ all is the ion content in the nutrient solution; γ is a constant; F is the average health status of the nutrient solution; MAX 、F MIN The state parameters of the nutrient solution samples to be tested are collected for the plant cultivation area corresponding to the sub-plant image data with the maximum information entropy and the minimum information entropy, and the nutrient solution health status performance value is obtained based on formula (1);

[0032] Among them, the average health status performance value of the nutrient solution The larger the value, the better the nutrient solution condition. Conversely, the smaller the value, the worse the nutrient solution condition. The constant γ is defined by the system user, and the constant γ>0.

[0033] Furthermore, the nutrient solution monitoring state determination threshold value set in the monitoring module is [a, b];

[0034] The monitoring logic of the nutrient solution safety in the monitoring module is expressed as follows:

[0035]

[0036] Where: is the latest health average state performance value of the three groups of nutrient solution based on the time sequence arrangement, and χ is a decay factor;

[0037] wherein, is Any one of the groups, the decay factor χ∈(0,1), formula (1), formula (2) is established, then it indicates that the nutrient solution is safe, otherwise, it indicates that the nutrient solution is unsafe.

[0038] Compared with the known public technology, the technical scheme provided by the present application has the following beneficial effects:

[0039] The present application provides a solution ion content automatic monitoring system based on Internet of Things, which, in the running process, analyzes the growth of the cultivated plants by image acquisition of the cultivated plants, so as to select two positions with the best and worst growth states as the nutrient solution sampling positions, sample the nutrient solution, further analyze the health state of the nutrient solution based on the set nutrient solution monitoring state analysis logic, and monitor the safety of the nutrient solution used for the cultivated plants according to the continuously analyzed nutrient solution health state, so as to bring online, intelligent and efficient nutrient solution real-time state health reference for the system end user, which is helpful for the system end user to manage the state of the nutrient solution used for the cultivated plants. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0041] Figure 1 It is a structure diagram of a solution ion content automatic monitoring system based on Internet of Things. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical scheme in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0043] The present application will be further described below in combination with the embodiments.

[0044] Embodiment 1:

[0045] The present embodiment is an automatic monitoring system for solution ion content based on the Internet of Things, such as Figure 1 Shown, including:

[0046] Camera module, used to collect image data of plants grown in plant factories;

[0047] The camera module is internally provided with submodules, including:

[0048] A segmentation unit, configured to receive plant image data collected by the camera module and perform segmentation processing on the plant image data;

[0049] A selection module is used to traverse the plant image data collected by the camera module and select a local area in the plant image data as the monitoring target area for this system operation;

[0050] A sampling module is used to receive the monitoring target area selected by the selection module and sample the solution for cultivating plants in the monitoring target area;

[0051] The sampling module is equipped with submodules, including:

[0052] The robotic arm module is used to carry the sampling pump and move it above the cultivated plants distributed in a matrix shape, reach the center of the cultivated plant area corresponding to the monitoring target area, and vertically push the sampling pump into the nutrient solution of the cultivated plants;

[0053] The sampling pump is used to collect three consecutive nutrient solution subsamples at the center of the plant cultivation area corresponding to each monitoring target area with its own pump suction end inserted into the nutrient solution;

[0054] The robotic arm module pushes the sampling pump into the nutrient solution for the plant cultivation, causing it to reach the bottom of the nutrient solution at a uniform speed. Each time the sampling pump reaches one-third of the depth of the nutrient solution, a subsample of the nutrient solution is collected. Three groups of nutrient solution subsamples collected at the center of the plant cultivation area in the same monitoring target area are mixed and recorded as one group of nutrient solution samples to be tested.

[0055] The sensing module is used to receive the sampled solutions from the sampling module and synchronously sense the state parameters of each group of solutions;

[0056] An analysis module is used to record in real time the state parameters of the sampled solution sensed by the sensing module and analyze the health status of the nutrient solution based on the state parameters of the sampled solution;

[0057] The health status analysis logic of the nutrient solution in the analysis module is expressed as:

[0058]

[0059] Where: F is the health status performance value of the nutrient solution presented by the state parameters of a group of nutrient solution samples to be tested; ρ NH , ρ HPO , ρ K , ρ CL , ρ NO is the content of ammonia ion, phosphorus ion, potassium ion, chloride ion and nitrite ion in the nutrient solution; ρ all is the ion content in the nutrient solution; γ is a constant; F is the average health status of the nutrient solution; MAX 、F MIN The state parameters of the nutrient solution samples to be tested are collected for the plant cultivation area corresponding to the sub-plant image data with the maximum information entropy and the minimum information entropy, and the nutrient solution health status performance value is obtained based on formula (1);

[0060] Among them, the average health status performance value of the nutrient solution The larger the value, the better the nutrient solution condition. Conversely, the smaller the value, the worse the nutrient solution condition. The constant γ is defined by the system user and is greater than 0.

[0061] The monitoring module is used to set the health determination threshold of the nutrient solution state, continuously receive the health status of the nutrient solution analyzed by the analysis module, and monitor the safety of the nutrient solution based on the health determination threshold of the nutrient solution state and the analysis results of the nutrient solution health state;

[0062] The nutrient solution monitoring status determination threshold set in the monitoring module is [a, b];

[0063] The monitoring logic of nutrient solution safety in the monitoring module is expressed as:

[0064]

[0065] Where: is the health status average performance value of the three groups of nutrient solutions obtained based on the latest time series; χ is the attenuation factor;

[0066] in, for For any group, if the attenuation factor χ∈(0,1), equations (1) and (2) hold, it means the nutrient solution is safe, otherwise, it means the nutrient solution is unsafe;

[0067] The camera module is interactively connected to the segmentation unit through a wireless network, the camera module and the segmentation unit are interactively connected to the selection module through a wireless network, the selection module is interactively connected to the sampling module through a wireless network, the sampling module is electrically connected to the robotic arm module and the sampling pump through a medium, and the sampling module is interactively connected to the perception module, the analysis module and the monitoring module through a wireless network.

[0068] In the embodiment, the camera module runs to collect plant image data in the plant factory, the segmentation unit synchronously receives the plant image data collected in the camera module, performs segmentation processing on the plant image data, the selection module runs behind to traverse the plant image data collected in the camera module, selects a local area in the plant image data as a monitoring target area of this system run, the sampling module further receives the monitoring target area selected in the selection module, samples the solution of the cultivated plant in the monitoring target area, the mechanical arm module synchronously carries the sampling pump to move above the cultivated plants distributed in a matrix, reaches the center position of the cultivated plant area corresponding to the monitoring target area, vertically pushes the sampling pump to extend into the nutrient solution of the cultivated plant, the sampling pump continuously performs three times of sampling of the nutrient solution sample at the center position of the cultivated plant area corresponding to each monitoring target area in the state of extending the pump suction end into the nutrient solution, the sensing module further receives the solution sampled in the sampling module, synchronously senses the state parameters of each group of solutions, and the analysis module records the state parameters of the sampled solution sensed by the sensing module in real time, analyzes the health state of the nutrient solution based on the state parameters of the sampled solution, and finally sets a nutrient solution state health determination threshold through the monitoring module, continuously receives the health state of the nutrient solution analyzed in the analysis module, and monitors the safety of the nutrient solution based on the nutrient solution state health determination threshold and the analysis result of the health state of the nutrient solution.

[0069] Through the system running in the above embodiment, the nutrient solution nutrient monitoring management service is provided for the plant factory to cultivate plants, so that the health state of the nutrient solution contacted by the cultivated plants is better maintained, sufficient nutrients are continuously provided for the cultivated plants, and the growth of the cultivated plants is guaranteed.

[0070] Embodiment 2:

[0071] In the specific implementation level, based on embodiment 1, the embodiment refers to Figure 1 Further specifically describe the solution ion content automatic monitoring system based on the Internet of Things in embodiment 1:

[0072] The camera module is arranged directly above the cultivated plants in the plant factory, the camera end of the camera module is vertically downward, and the camera module has a running period customized by a system end user, and the camera module continuously runs to collect plant image data based on the running period;

[0073] The plants cultivated in the plant factory are nutrient solution cultivation, the plants arranged in the plant factory are distributed in a matrix, the cultivated plant varieties distributed in a matrix are consistent, and the nutrient solution is consistent;

[0074] The image edge of the plant image data collected by the camera module coincides with the boundary of the cultivated plants distributed in a matrix;

[0075] The plant image data segmentation logic is set in the segmentation unit, the plant image data is segmented based on the plant image data segmentation logic in the segmentation unit, each image block obtained by the segmentation is recorded as sub-plant image data, the number of each sub-plant image data is not less than 2*2 groups, and the size and the aspect ratio of each sub-plant image data are equal;

[0076] The plant image data segmentation logic set in the processing unit is represented as:

[0077]

[0078] In the formula, m is the total amount of the sub-plant image data after the segmentation; q is the image segmentation base; f(i,j) is the frequency of the feature binary tuple (i,j); n is the scale of the image; and λ is the correction.

[0079] The correction λ≥1 and is subject to The greater the correction λ is, the greater the value of the correction λ is, and vice versa. The value of the image segmentation base q is 2*2 groups, the total amount m of the sub-plant image data after the segmentation is rounded up, and The value of is a positive integer, i represents the gray value of a pixel, and j represents the field gray mean value.

[0080] In the embodiment, the above setting provides further running logic support for the system running in embodiment 1, and the plant image data segmentation logic formula configuration described above makes the sampling position of the nutrient solution sample to be measured have precision control conditions, so that the system serves different scales of nutrient solution plant cultivation scenes and improves the system adaptability.

[0081] As shown in Figure 1 The selection module selects the local area in the plant image data, that is, the selection operation of the sub-plant image data. In the running stage of the selection module, the information entropy of each sub-plant image data is calculated, two groups of sub-plant image data are further selected, and the two groups of selected sub-plant image data are the sub-plant image data with the maximum and minimum information entropy.

[0082] The information entropy calculation logic of the sub-plant image data is

[0083] The above setting further limits the sampling position of the nutrient solution sample to be measured, and ensures that the nutrient solution sample to be measured is sampled at the specified position.

[0084] As shown in Figure 1 The perception module is integrated by the conductivity sensor and the microelectrode array sensor. The perception module receives the sampling solution in the sampling module, that is, the nutrient solution sample to be measured.

[0085] The state parameters of the nutrient solution sample to be tested sensed by the sensing module include: ion content, ammonia ion content, phosphorus ion content, potassium ion content, chloride ion content, and nitrite ion content in the nutrient solution.

[0086] Through the above settings, the state parameters of the nutrient solution sample to be tested are further limited.

[0087] In summary, during the operation of the system in the above embodiment, the growth conditions of the cultivated plants are analyzed by collecting images of the cultivated plants, and the two positions with the best and worst growth conditions are selected as nutrient solution sampling positions to sample the nutrient solution. The health status of the nutrient solution is further analyzed based on the set nutrient solution monitoring status analysis logic, and the safety of the nutrient solution used for cultivating plants is monitored by continuously analyzing the health status of the nutrient solution, providing system end users with an online, intelligent and efficient real-time health reference for the nutrient solution, which helps system end users to manage the status of the nutrient solution used for cultivating plants.

[0088] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An automatic monitoring system for solution ion content based on the Internet of Things, characterized in that: include: Camera module, used to collect image data of plants grown in plant factories; A selection module is used to traverse the plant image data collected by the camera module and select a local area in the plant image data as the monitoring target area for this system operation; A sampling module is used to receive the monitoring target area selected by the selection module and sample the solution for cultivating plants in the monitoring target area; The sensing module is used to receive the sampled solutions from the sampling module and synchronously sense the state parameters of each group of solutions; An analysis module is used to record in real time the state parameters of the sampled solution sensed by the sensing module and analyze the health status of the nutrient solution based on the state parameters of the sampled solution; The monitoring module is used to set the health determination threshold of the nutrient solution state, continuously receive the health status of the nutrient solution analyzed by the analysis module, and monitor the safety of the nutrient solution based on the health determination threshold of the nutrient solution state and the analysis results of the nutrient solution health state; The image edges in the plant image data collected by the camera module coincide with the boundaries of the cultivated plants distributed in a matrix. The camera module is internally provided with submodules, including: A segmentation unit, configured to receive plant image data collected by the camera module and perform segmentation processing on the plant image data; The segmentation unit sets a plant image data segmentation logic, and the segmentation unit segments the plant image data based on the plant image data segmentation logic. Each image block obtained by segmentation is recorded as sub-plant image data. The number of each sub-plant image data is no less than 2×2 groups, and the size and aspect ratio of each sub-plant image data are equal. The plant image data segmentation logic set in the segmentation unit is expressed as: ； Where: is the total amount of daughter plant image data after segmentation; is the image segmentation cardinality; is a feature binary Frequency of occurrence; is the scale of the image; To amend; Among them, the correction , and obey The larger the correction The larger the value, the smaller the correction The smaller the value, the higher the image segmentation cardinality. The value is 2×2 groups, the total amount of sub-plant image data after segmentation Round up, and The value of is a positive integer, i represents the gray value of the pixel, and j represents the gray mean of the field; The selection module performs a selection operation on the sub-plant image data. During the operation phase of the selection module, the information entropy of each sub-plant image data is calculated, and two groups of sub-plant image data are further selected, and the two groups of sub-plant image data selected are the sub-plant image data with the largest and smallest information entropy; Among them, the information entropy calculation logic of sub-plant image data is: ; The health status analysis logic of the nutrient solution in the analysis module is expressed as follows: ； Where: A nutrient solution health status performance value represented by a set of nutrient solution sample status parameters; 、 、 、 、 The content of ammonia ion, phosphorus ion, potassium ion, chloride ion and nitrite ion in the nutrient solution; is the ion content in the nutrient solution; is a constant; It is the average health status performance value of the nutrient solution; 、 The state parameters of the nutrient solution samples to be tested are collected for the plant cultivation area corresponding to the sub-plant image data with the maximum information entropy and the minimum information entropy, and the nutrient solution health status performance value is obtained based on formula (1); Among them, the average health status performance value of the nutrient solution The larger the value, the better the nutrient solution condition. Conversely, the smaller the value, the worse the nutrient solution condition. Defined by the system user, and the constant .

2. The automatic monitoring system for solution ion content based on the Internet of Things according to claim 1, characterized in that: The camera module is deployed directly above the cultivated plants in the plant factory, with the camera end of the camera module facing vertically downward, and the camera module has an operation cycle defined by a system user, and the camera module continuously operates to collect plant image data based on the operation cycle; Among them, the plants cultivated in the plant factory are cultivated with nutrient solution. The plants arranged in the plant factory are distributed in a matrix shape, and the cultivated plants in the matrix shape are of the same variety and nutrient solution.

3. The automatic monitoring system for solution ion content based on the Internet of Things according to claim 1, characterized in that: The sampling module is provided with submodules at the lower level, including: The robotic arm module is used to carry the sampling pump and move it above the cultivated plants distributed in a matrix shape, reach the center of the cultivated plant area corresponding to the monitoring target area, and vertically push the sampling pump into the nutrient solution of the cultivated plants; The sampling pump is used to collect three consecutive nutrient solution subsamples at the center of the plant cultivation area corresponding to each monitoring target area with its own pump suction end inserted into the nutrient solution; Among them, the robotic arm module pushes the sampling pump into the nutrient solution for growing plants, so that the sampling pump reaches the bottom of the nutrient solution at a uniform speed. Each time the sampling pump penetrates one-third of the depth of the nutrient solution, a nutrient solution sub-sample is collected. Three groups of nutrient solution sub-samples collected at the center position of the plant cultivation area corresponding to the same monitoring target area are mixed and recorded as a group of nutrient solution samples to be tested.

4. The automatic monitoring system for solution ion content based on the Internet of Things according to claim 1, characterized in that: The sensing module is integrated with a conductivity sensor and a microelectrode array sensor, and the sensing module operates to receive the sampling solution in the sampling module, that is, the nutrient solution sample to be tested; The state parameters of the nutrient solution sample to be tested sensed by the sensing module include: ion content, ammonia ion content, phosphorus ion content, potassium ion content, chloride ion content, and nitrite ion content in the nutrient solution.

5. The automatic monitoring system for solution ion content based on the Internet of Things according to claim 1, characterized in that: The nutrient solution health status determination threshold value set in the monitoring module is [a, b]; The monitoring logic of the nutrient solution safety in the monitoring module is expressed as follows: ； Where: In any group, the attenuation factor ∈(0,1), if formula (1) and formula (2) hold, it means that the nutrient solution is safe, otherwise, it means that the nutrient solution is unsafe.

6. The automatic monitoring system for solution ion content based on the Internet of Things according to claim 1, characterized in that: The camera module is interactively connected to a segmentation unit via a wireless network, the camera module and the segmentation unit are interactively connected to a selection module via a wireless network, the selection module is interactively connected to a sampling module via a wireless network, the sampling module is electrically connected to a robotic arm module and a sampling pump at a lower level via a medium, and the sampling module is interactively connected to a perception module, an analysis module and a monitoring module via a wireless network.

Images