Gas remote monitoring system based on Internet of Things

Abstract

The invention discloses a gas remote monitoring system based on Internet of Things, relates to the technical field of gas monitoring, and aims to monitor a gas environment in an agricultural greenhouse in real time, optimize crop growth conditions and improve production efficiency. The system collects gas concentration data in an agricultural greenhouse through a gas data sensor cluster, and uploads the data to a database for storage; the control analysis module extracts data in the database, calculates an air quality index and judges whether the gas data is normal or not; if the gas data is abnormal, the system informs an operator through sound-light alarm and information transmission; by monitoring the growth state of crops in real time, locking high-efficiency and low-efficiency agricultural greenhouses and dynamically updating the optimal gas data interval based on economic benefit evaluation and control cost analysis, optimization suggestions are provided for operators, and the operators are helped to optimize the gas environment in the agricultural greenhouses.

Description

Technical Field

[0001] The present invention belongs to the technical field of gas monitoring. Specifically, it relates to an on-line monitoring system for equipment based on artificial intelligence. Background Art

[0002] As a large agricultural country, with the continuous development of technology in China, the mode of agricultural production has gradually changed from the traditional manual method to semi-automation or even full automation. Among them, the application of gas detection technology in agricultural greenhouses has been gradually popularized. The rise of agricultural greenhouses helps operators to artificially control the growth environment of crops to a certain extent.

[0003] The existing technology still remains at the monitoring level in the detection of gas data in agricultural greenhouses, that is, only abnormal gases are monitored, and there are deficiencies in remote monitoring and intelligent management, and it is impossible to realize the real-time optimization and dynamic adjustment of the gas environment in agricultural greenhouses. Therefore, there is an urgent need for a more intelligent, precise and low-cost solution to meet the needs of modern agriculture; currently, the electrical control cabinet plays a key role in the automatic control of agricultural facilities, which can integrate various control modules and circuits to accurately supply power and control equipment; however, in the field of gas monitoring and management in agricultural greenhouses, there is no mature solution for deeply integrating the electrical control cabinet with the Internet of Things remote monitoring system; based on this, the present invention proposes a gas remote monitoring system based on the Internet of Things; using the electrical control cabinet as the core control unit and data transmission hub to realize the intelligent management of the gas environment in agricultural greenhouses. Summary of the Invention

[0004] In view of the deficiencies of the existing technology, the present invention provides a gas remote monitoring system based on the Internet of Things, which solves the problem that the existing technology only monitors but does not monitor the gas data in agricultural greenhouses.

[0005] The object of the present invention can be achieved by the following technical solutions:

[0006] A gas remote monitoring system based on the Internet of Things, the system includes the following:

[0007] A gas data acquisition module, which uses a gas data sensor cluster to real-time monitor the CO2 concentration, O2 concentration and harmful gas concentration in the agricultural greenhouse, and uploads the monitored gas data to the database module;

[0008] A control and analysis module, which extracts the gas data stored in the database module, judges whether the gas data in the agricultural greenhouse is normal, if the gas data is abnormal, immediately triggers an alarm to notify the operator, otherwise continues to monitor;

[0009] Real-time monitor the growth status of the crops in the current agricultural greenhouse under the influence of different gas data, and lock the high-efficiency agricultural greenhouses and low-efficiency agricultural greenhouses;

[0010] Continuously update the high-efficiency agricultural greenhouse, evaluate the optimal gas data range, and optimize the gas data in the agricultural greenhouse;

[0011] Database module, storing the analysis or calculation results of any step described in this solution;

[0012] Alarm module, notifying the operator of abnormal situations through audible and visual alarms and information transmission.

[0013] As a further solution of the present invention, the concentration of harmful gases in the gas data acquisition module is the total concentration of harmful gases, and the harmful gases include: NH3, CH4, C2H4;

[0014] The gas data sensor cluster in the gas data acquisition module is composed of multiple sensors that respectively measure the CO2 concentration, O2 concentration, and harmful gas concentration, without affecting each other.

[0015] As a further solution of the present invention, after the gas data acquisition module acquires gas data, it preliminarily processes the acquired gas data, and the specific method is as follows:

[0016] Obtain the area S of the agricultural greenhouse, and use the preset area S determined by the operator ' Divide the area S to obtain j area regions, and record them in the order of arrangement of the area regions as: S1, S2,..., S j , S i is any one of them, and both i and j are positive integer counting indexes, starting from 1, and i does not exceed j;

[0017] Based on the determined j area regions, deploy monitoring nodes and a gas data sensor cluster;

[0018] For the gas data collected by the gas data sensor cluster, the following method is used for processing. Taking the CO2 concentration as an example:

[0019] Obtain the j CO2 concentrations collected by the j gas data sensor clusters, denoted as the CO2 concentration sequence A1, A2,..., A j , obtain several CO2 concentration data of several agricultural greenhouses with the same crops as those in this agricultural greenhouse as historical CO2 concentration data, and construct an isolation forest model;

[0020] Input the CO2 concentration sequence A1, A2,..., A j into the isolation forest model in sequence, lock the abnormal CO2 concentration and the normal CO2 concentration, eliminate the abnormal CO2 concentration, and retain the normal CO2 concentration;

[0021] Based on several obtained normal CO2 concentrations, the CO2 concentration in the current agricultural greenhouse is obtained through an averaging operation:

[0022] Repeat the above steps to obtain the O2 concentration respectively and the concentration of harmful gases

[0023] The obtained CO2 concentration O2 concentration and the concentration of harmful gases along with the corresponding timestamps are jointly uploaded to the database module.

[0024] As a further solution of the present invention, the specific method for the control and analysis module to determine whether the gas data in the current agricultural greenhouse is normal is as follows:

[0025] Select crop X as the research object, and extract the CO2 concentration associated with the agricultural greenhouse where crop X is located from the database module O2 concentration and the concentration of harmful gases

[0026] Calculate the air quality index AQI in the current agricultural greenhouse, and then obtain the air quality index threshold AQI preset by the operator 阈 , if the calculated air quality index AQI > AQI 阈 , then the gas data in the agricultural greenhouse is regarded as abnormal;

[0027] If the concentration of harmful gases extracted is locked before calculating the air quality index exceeds the normal harmful gas concentration preset by the operator, then directly determine that the gas data in the agricultural greenhouse is abnormal and trigger an alarm to notify the operator.

[0028] As a further solution of the present invention, if the control and analysis module calculates that the air quality index AQI in the agricultural greenhouse ≤ AQI 阈 , then no treatment is performed and continuous monitoring is carried out.

[0029] As a further solution of the present invention, the specific method for the control and analysis module to lock high-efficiency agricultural greenhouses and low-efficiency agricultural greenhouses is as follows:

[0030] Select crop X as the research object, and all other types of crops are processed in this way;

[0031] Obtain the growth cycle formulated by the operator based on experience;

[0032] Select M agricultural greenhouses growing crop X. Using the method of controlling variables, ensure that except for the different gas data conditions, other conditions of the selected M agricultural greenhouses are the same;

[0033] Continuously monitor for one growth cycle to obtain any agricultural greenhouse G N The average CO2 concentration, average O2 concentration, and average harmful gas concentration during the growth cycle are combined and denoted as gas data characteristics. Obtain G during the growth cycle N The yield of growing X is converted into economic value and denoted as P X-N , and obtain the control cost when maintaining the gas data characteristics at the current standard during this growth cycle, denoted as H X-N , where G N represents any one of the M agricultural greenhouses, N starts from 1, and the maximum value is M;

[0034] Evaluate the economic value of the yield of X associated with each of the obtained M agricultural greenhouses and the control cost, and lock in high-efficiency agricultural greenhouses and low-efficiency agricultural greenhouses.

[0035] As a further solution of the present invention, the specific method for the control analysis module to lock in high-efficiency agricultural greenhouses and low-efficiency agricultural greenhouses further includes:

[0036] Sort the obtained M economic values in the order of the agricultural greenhouse sequence: G1, G2,..., G M , denoted as: P X-1 , P X-2 ,..., P X-M , and sort the obtained M control costs, denoted as: H X-1 , H X-2 ,..., H X-M ;

[0037] Construct a two-dimensional coordinate system with the agricultural greenhouse sequence as the horizontal axis and the amount as the vertical axis. Each agricultural greenhouse on the horizontal axis corresponds to two histogram columns, with the control cost on the left and the economic value on the right;

[0038] Map the M economic values and M control costs associated with the M agricultural greenhouses on the two-dimensional coordinate system;

[0039] Determine the midpoints at the tops of the histogram columns of the control cost and economic value of G N , draw a short line through the two points, and calculate the slope K of this short line N ;

[0040] Record the slopes of the short lines corresponding to each of the M agricultural greenhouses, denoted as K1, K2,..., K M , select the slope K of G N N, if K N ≤ 0, then lock G N as a low - efficiency agricultural greenhouse, otherwise lock G N as a high - efficiency agricultural greenhouse.

[0041] As a further solution of the present invention, the specific way for the control and analysis module to continuously update the high - efficiency agricultural greenhouse and evaluate the best gas data range is as follows:

[0042] Extract the slopes of all high - efficiency agricultural greenhouses during the current growth cycle, evaluate the high - efficiency agricultural greenhouse with the largest slope, and use its gas data characteristics as the best gas data during this growth cycle;

[0043] Continuously confirm O growth cycles, select a total of O high - efficiency agricultural greenhouses with the largest slopes and their gas data characteristics, split the gas data characteristics, and obtain O average CO2 concentrations, O average O2 concentrations, and O average harmful gas concentrations;

[0044] Extract the maximum and minimum values from the O average CO2 concentrations to form the best CO2 concentration range;

[0045] Obtain the best O2 concentration range and the best harmful gas concentration range respectively according to the above - mentioned processing method;

[0046] Combine the determined best CO2 concentration range, best O2 concentration range, and best harmful gas concentration range to obtain the best gas data range.

[0047] As a further solution of the present invention, the specific way for the control and analysis module to optimize the gas data in the agricultural greenhouse is as follows:

[0048] For any agricultural greenhouse where crop X is pre - planted or already planted, and the best gas data range of crop X determined;

[0049] The operator selects any set of gas data characteristics from the best gas data range as the gas data of the agricultural greenhouse where crop X is pre - planted or already planted during a growth cycle.

[0050] Advantages of the present invention:

[0051] (1) By adopting the method of controlling variables, the present invention establishes a multi-dimensional evaluation system. Through the comparative analysis of economic value and control cost, the input-output benefits of each agricultural greenhouse are quantified, breaking through the limitations of traditional empirical judgment. Secondly, the two-dimensional coordinate system slope analysis method is innovatively introduced to visually present the economic benefits, and the slope value is used to dynamically reflect the gas regulation efficiency, helping managers quickly identify the operating characteristics of high-benefit greenhouses and providing data support for resource allocation. Through continuous data tracking of multiple growth cycles, using extreme value statistics and interval optimization algorithms, the optimal gas concentration interval adapted to the needs of different crops is dynamically generated, realizing the iterative optimization of gas parameters and providing certain technical support for the digital upgrade of agricultural greenhouses.

[0052] (2) The present invention adopts a multi-dimensional sensor cluster design to simultaneously and independently monitor the concentrations of multiple gases, avoiding data interference and achieving full gas coverage detection, ensuring the integrity of environmental parameter acquisition. Secondly, by integrating spatial region division and anomaly detection algorithms, the isolation forest model is used to dynamically clean the data of multiple nodes, effectively eliminating the interference of sensor outliers. By establishing a multi-level early warning mechanism and combining the dynamic calculation of the air quality index and the double-track determination of the harmful gas threshold, the response to abnormal situations is realized, improving the efficiency compared with traditional manual inspections and effectively preventing the risk of crop poisoning. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The present invention will be further described below with reference to the accompanying drawings.

[0054] Figure 1 is a schematic structural diagram of the system of the present invention;

[0055] Figure 2 is a schematic flow diagram of the method described in Embodiment 2 of the present invention;

[0056] Figure 3 is a schematic flow diagram of the method described in Embodiment 3 of the present invention;

[0057] Figure 4 is a schematic diagram briefly showing the slope between the control cost and the economic value associated with the agricultural greenhouse described in Embodiment 4 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0058] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0059] Embodiment 1

[0060] An Internet of Things-based gas remote monitoring system, such as Figure 1 shown, specifically includes the following:

[0061] A gas data acquisition module uses a gas data sensor cluster to continuously monitor the CO2 concentration, O2 concentration, and harmful gas concentration in the agricultural greenhouse in real time, and uploads the monitored gas data to the database module. Specifically, for each agricultural greenhouse, a gas data sensor cluster installed inside the agricultural greenhouse continuously monitors the CO2 concentration, O2 concentration, and harmful gas concentration. One gas data sensor cluster includes a sensor for measuring the CO2 concentration, a sensor for measuring the O2 concentration, and a sensor for measuring the harmful gas concentration. The agricultural greenhouse is divided into zones by a preset area size, and each area will be regarded as a monitoring node. A set of gas data sensor clusters will be installed in each monitoring node to monitor the gas data in this monitoring node area, that is, the CO2 concentration, O2 concentration, and harmful gas concentration. The harmful gas concentration is the sum of multiple harmful gas concentrations, specifically: NH3, CH4, C2H4, and the sensors for measuring different gas data do not affect each other;

[0062] After the gas data sensor cluster measures the required gas data, it will transmit the measured gas data to the electrical control cabinet equipped in each agricultural greenhouse through a communication device or a system bus for marginal processing of the gas data, eliminate abnormal gas data, and upload the average gas concentration data at the current time node to the database module for data storage.

[0063] The control and analysis module, as the core module of this system, includes the following functions. It obtains the real-time concentration of various gas data of any agricultural greenhouse from the database module in real time, and based on double-track determination, realizes the response to abnormal situations. If an abnormal situation is detected in the agricultural greenhouse, it will send an abnormal command to the alarm module, and the alarm module will use the method of sound and light reminder to remind the operator. If the gas data of the detected agricultural greenhouse are all in a normal state, no processing will be done and continuous monitoring will be carried out.

[0064] Secondly, using the control variable method with gas data as the variable, it continuously monitors the yield of the crops in the agricultural greenhouse corresponding to different gas data conditions after the end of a growth cycle. Combining the economic value of the specific yield and the control cost of maintaining the gas data in the corresponding state, it locks in high-efficiency agricultural greenhouses and low-efficiency agricultural greenhouses. High-efficiency agricultural greenhouses represent agricultural greenhouses with high economic benefits, and similarly, low-efficiency agricultural greenhouses represent agricultural greenhouses with low economic benefits.

[0065] By continuously monitoring multiple agricultural greenhouses and multiple growth cycles, continuously obtaining the gas data corresponding to multiple high-efficiency agricultural greenhouses, and combining them into the best gas data interval. Subsequently, while optimizing the gas data of the agricultural greenhouse for pre-planting the corresponding crops, using the best gas data interval corresponding to this type of crop as the optimization standard. At the same time, when any abnormal situation occurs in the gas data monitored in a greenhouse growing this type of crop, the gas data in the agricultural greenhouse is optimized according to the best gas data interval of this type of crop through the electrical control cabinet equipped in the corresponding agricultural greenhouse.

[0066] In this solution, the optimization process mentioned refers to adjusting the gas data in the corresponding agricultural greenhouse to the best gas data interval suitable for the corresponding crop through the electrical control cabinet in the agricultural greenhouse.

[0067] The database module receives and stores the gas data of any agricultural greenhouse monitored and collected by the gas data acquisition module, and stores the results of any calculation step or analysis step described in this solution.

[0068] The alarm module receives the abnormal command transmitted by the control analysis module and notifies the operator of the abnormal situation in a timely manner by means of sound and light alarm and information transmission.

[0069] Embodiment 2

[0070] This embodiment discloses a method for determining whether the gas data in the current agricultural greenhouse is normal, as Figure 2 shown, specifically including the following:

[0071] For any determined agricultural greenhouse, obtain the actual area of the agricultural greenhouse, denoted as S. Generally, the actual area is planned and recorded at the beginning of the construction of the agricultural greenhouse. Therefore, the area S can be regarded as a known value. The operator combines the accuracy and power of the sensor for measuring gas data to formulate a preset area S ' , using the preset area S ' as the basis to divide the actual area S of the agricultural greenhouse. After division, a total of several area regions with an area of S ' are obtained. Here, for the convenience of subsequent calculation and representation, the several area regions with an area of S ' are briefly recorded as j area regions. According to the order in which the operator divides the agricultural greenhouse, the obtained j area regions are sorted, and the sorted j area regions are successively denoted as: S1, S2,..., S j , S i is any one of the area regions, and both i and j are positive integer counting indexes, starting from 1, and i does not exceed j, that is, i is included within 1 to.

[0072] Each area will be regarded as a separate monitoring node, and a cluster of gas data sensors for collecting gas data will be installed within this monitoring node to monitor the CO2 concentration, O2 concentration, and harmful gas concentration in real time;

[0073] In this embodiment, the CO2 concentration is taken as an example, and other gas data are processed in the same way as the CO2 concentration;

[0074] Based on the j monitoring nodes corresponding to the j area regions obtained, each time gas data is collected, j CO2 concentrations collected by the cluster of gas data sensors will be obtained, briefly recorded as the CO2 concentration sequence A1, A2,..., A j ;

[0075] Construct an isolation forest model, obtain the historical CO2 concentration data of several greenhouses that are the same as the crops in the currently monitored greenhouse, randomly extract 70% of the CO2 concentration data as the training set, and use the remaining 30% of the CO2 concentration data as the validation set. Use the training set to construct and train the isolation forest model, and use the validation set to evaluate the isolation forest model. Determine the isolation forest model corresponding to the best parameters through cross-validation;

[0076] Based on the CO2 concentration sequence A1, A2,..., A obtained from the above operations j , starting from A1, input A1 into the isolation forest model, and obtain a judgment result to lock A1 as normal CO2 concentration data or abnormal CO2 concentration data. According to the above processing method, judge the remaining j - 1 CO2 concentration data, eliminate all CO2 concentration data with abnormal judgment results, retain all normal CO2 concentration data, sum the obtained several normal CO2 concentration data, and then divide by the total number of normal CO2 concentration data to obtain the CO2 concentration in the current greenhouse at the current time point, denoted as

[0077] According to the method of processing the CO2 concentration in the current greenhouse above, obtain the O2 concentration in the current greenhouse and the harmful gas concentration

[0078] Obtain the currently obtained CO2 concentration O2 concentration harmful gas concentration The associated timestamps, the gas data collected by the cluster of gas data sensors, and the calculated average gas concentration data are all transmitted to the database module.

[0079] Then, the control and analysis module extracts the CO2 concentration of the current greenhouse from the database module O2 concentration Harmful gas concentration Adopt the formula:

[0080]

[0081] Calculate the air quality index AQI of the current agricultural greenhouse at the corresponding timestamp, where ω A is the calculation weight of CO2 concentration, ω B is the calculation weight of O2 concentration, ω C is the calculation weight of harmful gas concentration, ω A and ω B and ω C are all determined by the operator in combination with the actual situation and experience.

[0082] Then obtain the air quality index threshold AQI 阈 preset by the operator. If the air quality index AQI of the current agricultural greenhouse at the corresponding timestamp calculated exceeds the air quality index threshold AQI 阈 , then the gas data in the current agricultural greenhouse is regarded as abnormal;

[0083] It should be noted that before calculating the air quality index, first make a preliminary determination of the harmful gas concentration. If the extracted harmful gas concentration exceeds the normal harmful gas concentration preset by the operator, directly determine that the gas data in the current agricultural greenhouse is abnormal and transmit an abnormal command to the alarm module.

[0084] If the control analysis module calculates that the air quality index AQI of the current agricultural greenhouse at the corresponding timestamp is equal to or lower than the air quality index threshold AQI 阈 , then it is regarded that the air quality index AQI inside the current agricultural greenhouse is normal (gas data is normal), no processing is performed, and continuous monitoring is carried out.

[0085] Example 3

[0086] This example discloses a method for optimizing the gas data in an agricultural greenhouse with abnormal gas data and an agricultural greenhouse with pre-planted crops, as Figure 3 shown, specifically including the following:

[0087] This example analyzes and processes a single crop X, and the rest of the crops are processed according to the method described in this example;

[0088] Define the growth cycle according to the growth habits of the crop X. The growth cycle is a period of time determined by the operator, specifically the complete period from the planting time to the harvesting time of the crop X. The determination of the growth cycle needs to be representative, and the determination of the growth cycle of the same crop is the same and unique.

[0089] Select M agricultural greenhouses for growing crop X, and ensure that the only variable of the selected M agricultural greenhouses is gas data by using the method of controlling variables, while other conditions are the same.

[0090] After planting crop X in these M agricultural greenhouses, set different gas data conditions for the M agricultural greenhouses respectively, and continuously monitor the time of a growth cycle associated with crop X, and obtain any agricultural greenhouse G N The average CO2 concentration, average O2 concentration and average harmful gas concentration during this growth cycle time, and combine the data of these three gas concentrations, which is recorded as the gas data characteristics associated with agricultural greenhouse G N Then obtain the yield of crop X in the corresponding agricultural greenhouse G N And convert it into economic value (amount), briefly recorded as P X-N Then obtain the control cost when maintaining the gas data characteristics at the current standard during this growth cycle, and briefly record it as H X-N , where G N represents any one of the M agricultural greenhouses, N is a positive integer counting index, starting from 1, and the maximum value is M;

[0091] Then, according to the sorting order of the agricultural greenhouses marked by the operator: G1, G2,..., G M Sort the M economic values obtained, and record them in turn as: P X-1 , P X-2 ,..., P X-M , and sort the M control costs obtained, and record them in turn as: H X-1 , H X-2 ,..., H X-M ;

[0092] Taking the sorting sequence of agricultural greenhouses G1, G2,..., G M as the horizontal axis and the amount value as the vertical axis, construct a two-dimensional coordinate system. Each agricultural greenhouse on the horizontal axis corresponds to two histogram columns, namely the control cost on the left and the economic value on the right;

[0093] The M agricultural greenhouses G1, G2,..., G M in the sorting sequence of agricultural greenhouses G1, G2,..., G M The M economic values P associated with...X-1 , P X-2 ,..., P X-M and M control costs H X-1 , H X-2 ,..., H X-M They are respectively surveyed and mapped in the constructed two-dimensional coordinate system;

[0094] Then determine any agricultural greenhouse G N The midpoint at the top of the histogram constructed in the two-dimensional coordinate system for the control cost and economic value of the greenhouse, draw short lines through the two points respectively, and by calculating the slope of this short line, obtain the slope K N between the associated control cost and economic value of agricultural greenhouse G N , the slope K N The larger the value of the slope K N indicates that the economic benefit of agricultural greenhouse G N is better, representing more amount after subtracting the control cost from the economic value. On the contrary, the smaller the value of the slope K N indicates that the economic benefit of agricultural greenhouse G Figure 4 );

[0095] Record the slopes corresponding to each of the M agricultural greenhouses G1, G2,..., G M in the order of the greenhouse sequence G1, G2,..., G M and denote them as K1, K2,..., K M respectively. Evaluate the M obtained slopes, select any slope K N . If K N is less than or equal to 0, then lock the agricultural greenhouse G N corresponding to K N as a low-efficiency agricultural greenhouse. If K N is greater than 0, then lock the agricultural greenhouse G N corresponding to K N as a high-efficiency agricultural greenhouse.

[0096] For the high-efficiency agricultural greenhouses determined during this growth cycle among the agricultural greenhouses G1, G2,..., G M , extract the slope corresponding to this high-efficiency agricultural greenhouse, and evaluate the gas data characteristics associated with the high-efficiency agricultural greenhouse with the largest slope value among all slopes as the best gas data during this growth cycle;

[0097] Continuously confirm O growth cycles, and respectively extract the M selected agricultural greenhouses G1, G2,..., G MAmong the calibrated different gas data characteristics, successively select the gas data characteristics associated with the high-efficiency agricultural greenhouse with the largest slope, and split the obtained O gas data characteristics to obtain O average CO2 concentrations, O average O2 concentrations, and O average harmful gas concentrations;

[0098] Based on the obtained O average CO2 concentrations, extract the maximum value and the minimum value respectively to form the optimal CO2 concentration range; based on the obtained O average O2 concentrations, extract the maximum value and the minimum value respectively, and jointly form the optimal O2 concentration range with the remaining O-2 average O2 concentrations; based on the obtained O average harmful gas concentrations, extract the maximum value and the minimum value respectively, and jointly form the optimal harmful gas concentration range with the remaining O-2 average harmful gas concentrations;

[0099] Based on the determined optimal CO2 concentration range, optimal O2 concentration range, and optimal harmful gas concentration range, perform combination processing to obtain the optimal gas data range.

[0100] The operator selects any set of gas data from the optimal gas data range, including a CO2 concentration, an O2 concentration, and a harmful gas concentration, and uses the selected CO2 concentration, O2 concentration, and harmful gas concentration as the gas data of the agricultural greenhouse for the pre-planted crop X during a growth cycle. Through optimization processing, ensure that the gas data concentration is maintained at the gas data selected by the operator;

[0101] The above optimization processing is to control gas data through existing technologies, such as ventilation operations, etc., which will not be elaborated here;

[0102] In addition to the above, when the gas data monitored in any agricultural greenhouse where the crop X has been planted is abnormal, the operator also selects a set of gas data from this optimal gas data range for optimization operations.

[0103] Some of the data in the above formulas are numerically calculated after removing their dimensions, and the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0104] The above content is only an example and explanation of the present invention. Those skilled in the art of this technology make various modifications or supplements to the described specific embodiments or use similar methods to replace them. As long as they do not deviate from the invention or exceed the scope defined by this claim book, they should fall within the protection scope of the present invention.

[0105] It should be noted that: All user data collected in this application is collected with the consent and authorization of the users. Moreover, the uses of the user data are legal and compliant, and the use and processing of the user data comply with the relevant laws, regulations and standards of the relevant regions.

Claims

1. The gas remote monitoring system based on the Internet of Things is characterized in that The system includes the following: A gas data acquisition module that uses a gas data sensor cluster to continuously monitor the CO2 concentration, O2 concentration, and harmful gas concentration in the agricultural greenhouse, and uploads the monitored gas data to the database module; A control and analysis module that extracts the gas data stored in the database module, determines whether the gas data in the agricultural greenhouse is normal. If the gas data is abnormal, it immediately triggers an alarm to notify the operator; otherwise, it continues to monitor; Continuously monitor the growth status of the crops in the current agricultural greenhouse under the influence of different gas data, and identify high-efficiency and low-efficiency agricultural greenhouses; Continuously update high-efficiency agricultural greenhouses, evaluate the optimal gas data range, and optimize the gas data in the agricultural greenhouses; A database module that stores the analysis or calculation results of any step described in this solution; An alarm module that notifies the operator of abnormal situations through audible and visual alarms and information transmission.

2. The gas remote monitoring system based on the Internet of Things according to claim 1, characterized in that The harmful gas concentration described in the gas data acquisition module is the total concentration of harmful gases, and the harmful gases include: NH3, CH4, C2H4; The gas data sensor cluster described in the gas data acquisition module is composed of multiple sensors that respectively measure the CO2 concentration, O2 concentration, and harmful gas concentration, without mutual influence.

3. The gas remote monitoring system based on the Internet of Things according to claim 2, characterized in that After the gas data acquisition module collects gas data, it performs preliminary processing on the collected gas data. The specific method is as follows: Obtain the area S of the agricultural greenhouse, with the preset area S determined by the operator ′ Divide the area S to obtain j area regions, and denote them in the arrangement order of the area regions as: S1, S2,..., Si j , Si i where Si is any one of them, and both i and j are positive integer counting indices, starting from 1, and i does not exceed j; Based on the determined j area regions, deploy monitoring nodes and a gas data sensor cluster; For the gas data collected by the gas data sensor cluster, the following method is used for processing. Taking the CO2 concentration as an example: Obtain the j CO2 concentrations collected by j gas data sensor clusters, denoted as the CO2 concentration sequences A1, A2,..., A j , obtain several CO2 concentration data of several agricultural greenhouses that are the same as the crops in this agricultural greenhouse as historical CO2 concentration data, and construct an isolation forest model; Input the CO2 concentration sequences A1, A2,..., A j into the lonely forest model in sequence, lock the abnormal CO2 concentration and the normal CO2 concentration, eliminate the abnormal CO2 concentration, and retain the normal CO2 concentration; Based on a number of obtained normal CO2 concentrations, the CO2 concentration in the current agricultural greenhouse is obtained through an averaging operation: Repeat the above steps to obtain the O2 concentration and the harmful gas concentration respectively and the harmful gas concentration Upload the obtained CO2 concentration O2 concentration and the harmful gas concentration to the database module jointly with the corresponding timestamps.

4. The gas remote monitoring system based on the Internet of Things according to claim 3, characterized in that, The specific method for the control and analysis module to determine whether the gas data in the current agricultural greenhouse is normal is: Select crop X as the research object, and extract the CO2 concentration A, O2 concentration B, and harmful gas concentration C associated with the agricultural greenhouse where crop X is located from the database module; Calculate the Air Quality Index (AQI) inside the current agricultural greenhouse, and then obtain the air quality index threshold AQI preset by the operator 阈 , if the calculated Air Quality Index AQI > AQI 阈 , then consider the gas data inside the agricultural greenhouse as abnormal; If, before calculating the air quality index, it is determined that the extracted harmful gas concentration C exceeds the normal harmful gas concentration preset by the operator, it is directly determined that the gas data in the agricultural greenhouse is abnormal, and an alarm is triggered to notify the operator.

5. The gas remote monitoring system based on the Internet of Things according to claim 4, characterized in that, If the control analysis module calculates that the air quality index AQI in the agricultural greenhouse satisfies AQI ≤ AQI 阈 , no treatment is performed and continuous monitoring is carried out.

6. The gas remote monitoring system based on the Internet of Things according to claim 5, characterized in that, The specific method for the control and analysis module to identify high-efficiency and low-efficiency agricultural greenhouses is: Select crop X as the research object, and all other types of crops are processed in this way; Obtain the growth cycle formulated by the operator based on experience; Select M agricultural greenhouses where crop X is planted, and use the control variable method to ensure that the selected M agricultural greenhouses have the same other conditions except for different gas data conditions; Continuously monitor a growth cycle to obtain any agricultural greenhouse G N The average CO2 concentration, average O2 concentration, and average harmful gas concentration during the growth cycle are combined and denoted as gas data characteristics, and obtain G during the growth cycle N The yield of planting X is converted into economic value and denoted as P X-N Obtain the control cost when the gas data characteristics are maintained at the current standard during this growth cycle, denoted as H X-N where G N represents any one of the M agricultural greenhouses, N starts from 1, and the maximum value is M; Evaluate the economic value of the yield of X and the control cost associated with each of the obtained M agricultural greenhouses, and identify high-efficiency and low-efficiency agricultural greenhouses.

7. The gas remote monitoring system based on the Internet of Things according to claim 6, characterized in that The specific method for the control and analysis module to identify high-efficiency and low-efficiency agricultural greenhouses also includes: According to the sequence of agricultural greenhouses: G1, G2,..., G M Sort the obtained M economic values in the order of, denoted as: P X-1 , P X-2 ,..., P X-M , and sort the obtained M control costs, denoted as: H X-1 , H X-2 ,..., H X-M ; Construct a two-dimensional coordinate system with the agricultural greenhouse sequence as the horizontal axis and the amount as the vertical axis. Each agricultural greenhouse on the horizontal axis corresponds to two histogram columns, with the control cost on the left and the economic value on the right; Map the M economic values and M control costs associated with M agricultural greenhouses on a two-dimensional coordinate system; Determine G N For the histogram of the control cost and economic value of N , find the midpoint at the top of the bar, draw a short line through the two points, and calculate the slope K of this short line N ; Record the slopes of the short lines corresponding to each of the M agricultural greenhouses, denoted as K1, K2, ..., K M , select G N 's slope K N . If K N ≤0, then lock G N as a low-efficiency agricultural greenhouse; otherwise, lock G N as a high-efficiency agricultural greenhouse.

8. The gas remote monitoring system based on the Internet of Things according to claim 7, characterized in that, The specific method for the control analysis module to continuously update high-efficiency agricultural greenhouses and evaluate the optimal gas data range is as follows: During this growth cycle, extract the slopes of all high-efficiency agricultural greenhouses, evaluate the high-efficiency agricultural greenhouse with the largest slope, and use its gas data characteristics as the optimal gas data for this growth cycle; Continuously confirm O growth cycles, select a total of O high-efficiency agricultural greenhouses with the largest slopes and their gas data characteristics, split the gas data characteristics, and obtain O average CO2 concentrations, O average O2 concentrations, and O average harmful gas concentrations; Extract the maximum and minimum values from the O average CO2 concentrations to form the optimal CO2 concentration range; Obtain the optimal O2 concentration range and the optimal harmful gas concentration range respectively according to the above processing method; Combine the determined optimal CO2 concentration range, optimal O2 concentration range, and optimal harmful gas concentration range to obtain the optimal gas data range.

9. The gas remote monitoring system based on the Internet of Things according to claim 8, characterized in that The specific method for the control analysis module to optimize the gas data in agricultural greenhouses is as follows: For any agricultural greenhouse that pre-plants or has planted crop X, and the determined optimal gas data range for crop X; The operator selects any set of gas data characteristics from the optimal gas data range as the gas data of the agricultural greenhouse that pre-plants or has planted crop X in a growth cycle.

Images