CN113157030A - Greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning - Google Patents

Greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning Download PDF

Info

Publication number
CN113157030A
CN113157030A CN202110496029.3A CN202110496029A CN113157030A CN 113157030 A CN113157030 A CN 113157030A CN 202110496029 A CN202110496029 A CN 202110496029A CN 113157030 A CN113157030 A CN 113157030A
Authority
CN
China
Prior art keywords
humidity
temperature
greenhouse
data
alarm
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110496029.3A
Other languages
Chinese (zh)
Inventor
王鑫
张奇志
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Shiyou University
Original Assignee
Xian Shiyou University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xian Shiyou University filed Critical Xian Shiyou University
Priority to CN202110496029.3A priority Critical patent/CN113157030A/en
Publication of CN113157030A publication Critical patent/CN113157030A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
    • G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Greenhouses (AREA)

Abstract

The invention provides a greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning; the method comprises the following steps: temperature and humidity monitoring module, wireless transceiver, host computer, microprocessor unit, alarm device and temperature and humidity adjusting device. According to the method, the machine learning prediction model is established by collecting historical temperature and humidity data of the greenhouse, the real-time change trend of the temperature and the humidity in the greenhouse can be predicted timely and accurately, the environmental factors in the greenhouse are adjusted properly, unnecessary loss is reduced, and the method has a high practical value.

Description

Greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning
Technical Field
The invention belongs to the technical field of intelligent agriculture; in particular to a greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning.
Background
With the vigorous popularization of a novel agricultural greenhouse planting technology in China, the number of greenhouses is more and more; due to the influence of various factors such as high cost and certain technical content of the intelligent greenhouse, most of the greenhouses adopt an artificial method to control the environmental conditions in the greenhouse. Even greenhouse growers with years of experience cannot effectively control various environmental factors in the greenhouse. In the prior art, the management of the greenhouse by adopting a manual method is time-consuming and labor-consuming, and sometimes unnecessary losses occur due to carelessness of managers. Therefore, if the automatic monitoring control device which is low in cost and easy to operate can be designed, the environmental factors in the greenhouse can be monitored, predicted and controlled through the automatic monitoring control device which can be widely used, when the system predicts that the temperature and humidity will exceed normal values, an alarm can be sent to remind a grower and timely adjust the temperature and humidity, and unnecessary loss is avoided.
Disclosure of Invention
The invention aims to provide a greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning. The invention aims to solve the problem and can timely and accurately adjust the environmental factors such as temperature, humidity and the like in the greenhouse so as to reduce inconvenience caused by manual operation and reduce unnecessary loss.
The invention is realized by the following technical scheme:
the invention relates to a greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning, which comprises: the temperature and humidity monitoring system comprises a temperature and humidity monitoring module, a wireless transceiver, an upper computer, a microprocessor unit, an alarm device and a temperature and humidity adjusting device;
wherein the content of the first and second substances,
humiture monitoring module includes: the device comprises an air temperature and humidity sensor, a soil humidity sensor and an AD conversion module; the signals measured by the air temperature and humidity and soil humidity sensors are analog signals, and the AD converter converts the analog signals into digital signals for further processing;
the wireless transceiver device comprises: a wireless signal transmitting device and a wireless signal receiving device; the wireless signal sending device is mutually connected with each measuring point distributed in the greenhouse through a CAN bus, so that real-time data transmission is realized; the wireless signal receiving device is connected with an upper computer through a CAN bus and transmits data to the upper computer in real time;
the upper computer is used for receiving data transmitted from the wireless signal receiving end in real time and inputting the data into a temperature and humidity prediction model in the upper computer for real-time data analysis and prediction;
the microprocessor unit is connected with an upper computer through a serial port; when the prediction model in the upper computer predicts that the temperature and humidity value in the greenhouse is about to exceed the normal range value, the upper computer sends a finger to the micro-processing unit and the alarm device; after receiving the instruction, the microprocessor sends a control instruction to the temperature and humidity adjusting module and the alarm device, and starts a corresponding adjusting alarm mechanism to work;
the alarm device comprises: a voice alarm and an alarm bell; the alarm device receives an alarm signal sent by the microprocessor, starts the voice alarm and broadcasts the environmental condition in the greenhouse in real time; meanwhile, an alarm ring is sounded to timely remind a grower that the temperature and the humidity in the greenhouse are abnormal;
temperature humidity control device includes: a temperature adjusting device and a humidity adjusting device; the temperature adjusting device comprises a warm air blower, an exhaust fan, a shading curtain on the top and the side of the greenhouse and a corresponding driving motor; the humidity adjusting device comprises an air dehumidifier, a near-ground blower and an automatic spraying device. It should be noted that the temperature and humidity change is not a rapid process, and the temperature and humidity adjustment needs a certain time. Therefore, it is necessary to set the temperature/humidity upper and lower limit fluctuation ranges.
Preferably, the specific steps of establishing the temperature and humidity prediction model in the upper computer are as follows:
step 1, collecting historical data of temperature and humidity in the greenhouse.
And 2, performing data preprocessing on the collected historical data to construct a training data set and a test data set for predicting the temperature and the humidity.
And 3, training the training data set through a machine learning algorithm to obtain a prediction model. And testing the prediction model by using the test data set, and outputting a corresponding confidence coefficient.
Preferably, the data preprocessing in step 2 mainly comprises data cleaning and data standardization.
Preferably, the machine learning algorithm in step 3 is a ridge regression algorithm in linear regression. In this application, the predicted independent variables are the temperature and humidity within the greenhouse. The two variables have large collinearity, so that the matrix X of the input data is not a full-rank matrix, and an unsolvable problem can occur in the subsequent solving process. Ridge regression is actually an improved least squares estimation.
The invention has the following advantages: according to the method, the machine learning prediction model is established by collecting historical temperature and humidity data of the greenhouse, the real-time change trend of the temperature and the humidity in the greenhouse can be predicted timely and accurately, and environmental factors in the greenhouse are adjusted appropriately, so that unnecessary loss is reduced, and the method has a high practical value.
Drawings
Fig. 1 is a structural diagram of a greenhouse temperature and humidity monitoring and adaptive adjusting system based on machine learning.
Detailed Description
The present invention will be described in detail with reference to specific examples. It should be noted that the following examples are only illustrative of the present invention, but the scope of the present invention is not limited to the following examples.
Examples
This embodiment relates to a big-arch shelter humiture monitoring and self-adaptation governing system based on machine learning, includes: as shown in fig. 1: temperature and humidity monitoring module, wireless transceiver, host computer, microprocessor unit, alarm device and temperature and humidity adjusting device.
The temperature and humidity monitoring module sends acquired real-time temperature and humidity data through the transmitting device, the wireless receiving device receives the data values and transmits the data values to the upper computer, and the upper computer receives the data values and inputs the data values into a temperature and humidity prediction model which is trained in advance by using a machine learning mode to perform real-time analysis and prediction. And if the prediction model predicts that the temperature and humidity value in the greenhouse is about to exceed the temperature and humidity upper and lower limit value preset by the grower, the upper computer sends an instruction to the microprocessor unit. The microprocessor is connected with the alarm device and the temperature and humidity adjusting module. After the alarm module receives the alarm signal from the microprocessor, an alarm mechanism is triggered to prompt the greenhouse growers. Meanwhile, after receiving the instruction sent by the upper computer, the microprocessor sends a starting instruction to start the corresponding temperature and humidity adjusting device to adjust the temperature and humidity in the greenhouse. The upper computer receives real-time monitoring data provided by the temperature and humidity monitoring module, and if the real-time temperature and humidity in the greenhouse are within a preset normal temperature and humidity floating range, the upper computer sends an instruction to drive the corresponding adjusting module to be closed, so that the effect of self-adaptive adjustment of the temperature and humidity of the greenhouse is achieved.
The temperature and humidity monitoring module comprises an air temperature and humidity sensor, a soil humidity sensor and an AD conversion module. The signals measured by the air temperature and humidity and soil humidity sensors are analog signals, and the AD converter converts the analog signals into digital signals for further processing.
The wireless transceiver comprises a wireless signal transmitting device and a wireless signal receiving device. The wireless signal sending device is connected with each measuring point (measuring point 1 and measuring point 2 … … measuring n) distributed in the greenhouse through the AD converter through the CAN bus, so that real-time data transmission is realized; the wireless signal receiving device is connected with an upper computer through a CAN bus and transmits data to the upper computer in real time.
The upper computer receives temperature and humidity data transmitted from the wireless signal receiving end in real time, and the data are input into a temperature and humidity prediction model in the upper computer to carry out real-time data analysis and prediction. The temperature and humidity prediction model is established by the following specific steps:
step 1, collecting historical data of temperature and humidity in the greenhouse.
And 2, performing data preprocessing on the collected historical data to construct a training data set and a test data set for predicting the temperature and the humidity.
And 3, training the training data set through a machine learning algorithm to obtain a prediction model. And testing the prediction model by using the test data set, and outputting a corresponding confidence coefficient.
The temperature and humidity prediction model is characterized in that the data preprocessing in the step 2 mainly comprises data cleaning and data standardization.
The data cleaning mainly comprises the step of processing missing values and abnormal values of collected historical data.
The processing of missing values depends mainly on the importance of the attribute and the missing rate. If the data loss rate is low and the importance degree of the attributes is low, filling the loss value by using the average value; if the missing rate of the data is high (more than 90 percent) and the importance degree of the attribute is low, directly deleting the missing value; if the data missing rate is high and the importance degree of the attributes is high, filling missing values by a modeling method.
The modeling method is to predict the data of the missing value by using the attributes of other data in the data set through models such as regression, decision tree, random forest and Bayes, and use the prediction result to fill the missing value.
Three processing methods are generally adopted for outlier processing: and directly deleting missing values, not processing abnormal values, regarding the abnormal values as missing values, and filling the missing values. If the abnormal value is few and obviously observable abnormal value can be directly deleted; when the adopted algorithm is insensitive to the abnormal value, the abnormal value can be reserved and not processed; otherwise, corresponding processing can be carried out according to the missing value processing mode.
The data is standardized by a min-max method. The concrete formula is
Figure BDA0003054312010000051
Wherein x' represents the normalized data, x is the raw data value, min is the minimum value in the raw data, and max is the maximum value in the raw data.
In step 3, the machine learning algorithm is a ridge regression algorithm in linear regression. In the present invention, the predicted independent variables are the temperature and humidity within the greenhouse. The two variables have large collinearity, so that the matrix X of the input data is not a full-rank matrix, and an unsolvable problem can occur in the subsequent solving process. Ridge regression is actually an improved least squares estimation.
The ridge regression algorithm comprises the following specific steps:
step 1, D ═ x for the dataset(1),y(1))；(x(2),y(2))；...(x(i),y(i)) Where x) is(i)Representing the ith sample point, and establishing a multiple linear regression prediction model:
hθ(x(i))＝θ0+θ1x1 (i)+θ2x2 (i)+...+θjxj (i) (1.1)
wherein h isθ(x(i)) Indicates the predicted value, thetajRepresenting model parameters, θ0Biasing for the model
Equation 1.1 can be written as the following vector expression:
hθ(x(i))＝θTx(i) (1.2)
step 2, the matrix form of the loss function is
Figure BDA0003054312010000052
Wherein:
Figure BDA0003054312010000053
representing training sample data;
Y＝[y(1),y(2)...y(n)]Trepresenting a vector formed by all training sample outputs;
θ＝[θ0,θ1,...θn]Tare regression coefficients.
Step 3, solving the regression coefficient θ may be regarded as solving an optimization problem:
Figure BDA0003054312010000054
the solution is obtained by adopting a least square method as follows:
θ＝(XTX)-1XTy (1.5)
when matrix XTWhen X is not reversible, i.e. the arguments have collinearity, θ has no solution, when l of the parameter is added to the original loss function2Norm penalty, the optimization problem becomes:
Figure BDA0003054312010000061
wherein, λ is a nonnegative number, and the larger λ is, the more obvious the effect of the penalty term is.
Taking the derivative of equation 1.6 with respect to θ, let the derivative be zero, yields:
θ＝(XTX+λI)-1XTy (1.7)
from equation 1.7, it can be seen that θ is a function of λ, and when λ is non-negative, a curve of θ - λ is plotted in a planar rectangular coordinate system, called a ridge trace. When theta tends to be stable, the corresponding lambda value is the value to be searched.
And 4, solving the theta value, substituting the theta value into the formula 1.1 to obtain a corresponding predicted value hθ(x(i))。
And the microprocessor unit is connected with an upper computer through serial port communication. And when the prediction model in the upper computer predicts that the temperature and humidity value in the greenhouse is about to exceed the normal range value, the upper computer sends an instruction to the micro-processing unit and the alarm device. After receiving the instruction, the microprocessor unit sends a control instruction to the temperature and humidity adjusting module and the alarm device, and starts a corresponding adjusting alarm mechanism to work.
The alarm device comprises a voice alarm and an alarm bell. The alarm device receives an alarm signal sent by the microprocessor unit, starts the voice alarm and broadcasts the environmental condition in the greenhouse in real time; meanwhile, an alarm ring is sounded to timely remind that the temperature and the humidity in the greenhouse of the planting house are abnormal.
The temperature and humidity adjusting device comprises a temperature adjusting device and a humidity adjusting device. The temperature adjusting device comprises a warm air blower, an exhaust fan, a shading curtain on the top and the side of the greenhouse and a corresponding driving motor; the humidity adjusting device comprises an air dehumidifier, a near-ground blower and an automatic spraying device. The temperature and humidity change is not a rapid process, and the temperature and humidity adjustment needs a certain time to change. Therefore, it is necessary to set the temperature/humidity upper and lower limit fluctuation ranges.
Exhaust fan among the temperature regulation apparatus and the window shade effect at big-arch shelter top and side are: when the temperature in the greenhouse is predicted to exceed the normal level, the microprocessor sends an instruction to the driving motor to drive the top and the side shading curtains of the greenhouse to be closed, so that direct sunlight is avoided. Meanwhile, the exhaust fan is started to accelerate the air flow in the greenhouse. Under the combined action of the exhaust fan and the shading curtain, the purpose of cooling is achieved.
The warm air blower in the temperature adjusting device has the following functions: when the temperature in the greenhouse is predicted to be lower than the normal level, the microprocessor sends an instruction to the driving motor to drive the fan heater motor to work, and the purpose of increasing the temperature is achieved.
The air dehumidifier and the near-ground blower in the humidity adjusting device have the following functions: when the soil humidity in the greenhouse is predicted to be higher than the normal level, the microprocessor sends an instruction to start the air dehumidifier to reduce the humidity value of the air. Meanwhile, the near-ground blower works, and the purpose of reducing the soil humidity is achieved by accelerating the near-ground air flow rate.
The automatic spraying device in the humidity adjusting device has the following functions: when the soil humidity value in the greenhouse is predicted to be lower than the normal level, the microprocessor sends an instruction to start the automatic spraying device, so that the humidity values in the air and the soil are increased. In addition, the spraying device can also be used as a cooling device.
The temperature adjusting device and the humidity adjusting device are connected with the microprocessor unit through RS485 buses.
The temperature and humidity monitoring module sends acquired real-time temperature and humidity data through the transmitting device, the wireless receiving device receives the data values and transmits the data values to the upper computer, and the upper computer receives the data values and inputs the data values into a temperature and humidity prediction model which is trained in a machine learning mode in advance to perform real-time analysis and prediction. And if the prediction model predicts that the temperature and humidity value in the greenhouse is about to exceed the temperature and humidity upper and lower limit value preset by the grower, the upper computer sends an instruction to the microprocessor unit. The microprocessor is connected with the alarm device and the temperature and humidity adjusting module. After the alarm module receives the alarm signal from the microprocessor, an alarm mechanism is triggered to prompt the greenhouse growers. Meanwhile, after receiving the instruction sent by the upper computer, the microprocessor sends a starting instruction to start the corresponding temperature and humidity adjusting device to adjust the temperature and humidity in the greenhouse. The upper computer receives real-time monitoring data provided by the temperature and humidity monitoring module, and if the real-time temperature and humidity in the greenhouse are within a preset normal temperature and humidity floating range, the upper computer sends an instruction to drive the corresponding adjusting module to be closed, so that the effect of self-adaptive adjustment of the temperature and humidity of the greenhouse is achieved.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention.

Claims (4)

1. The utility model provides a big-arch shelter humiture monitoring and self-adaptation governing system based on machine learning which characterized in that includes: the temperature and humidity monitoring system comprises a temperature and humidity monitoring module, a wireless transceiver, an upper computer, a microprocessor unit, an alarm device and a temperature and humidity adjusting device;
wherein the content of the first and second substances,
humiture monitoring module includes: the device comprises an air temperature and humidity sensor, a soil humidity sensor and an AD conversion module; the signals measured by the air temperature and humidity and soil humidity sensors are analog signals, and the AD converter converts the analog signals into digital signals for further processing;
the wireless transceiver device comprises: a wireless signal transmitting device and a wireless signal receiving device; the wireless signal sending device is mutually connected with each measuring point distributed in the greenhouse through a CAN bus, so that real-time data transmission is realized; the wireless signal receiving device is connected with an upper computer through a CAN bus and transmits data to the upper computer in real time;
the upper computer is used for receiving data transmitted from the wireless signal receiving end in real time and inputting the data into a temperature and humidity prediction model in the upper computer for real-time data analysis and prediction;
the microprocessor unit is connected with an upper computer through a serial port; when the prediction model in the upper computer predicts that the temperature and humidity value in the greenhouse is about to exceed the normal range value, the upper computer sends a finger to the micro-processing unit and the alarm device; after receiving the instruction, the microprocessor sends a control instruction to the temperature and humidity adjusting module and the alarm device, and starts a corresponding adjusting alarm mechanism to work;
the alarm device comprises: a voice alarm and an alarm bell; the alarm device receives an alarm signal sent by the microprocessor, starts the voice alarm and broadcasts the environmental condition in the greenhouse in real time; meanwhile, an alarm ring is sounded to timely remind a grower that the temperature and the humidity in the greenhouse are abnormal;
temperature humidity control device includes: a temperature adjusting device and a humidity adjusting device; the temperature adjusting device comprises a warm air blower, an exhaust fan, a shading curtain on the top and the side of the greenhouse and a corresponding driving motor; the humidity adjusting device comprises an air dehumidifier, a near-ground blower and an automatic spraying device.
2. The machine learning-based greenhouse temperature and humidity monitoring and adaptive adjusting system of claim 1, wherein the specific steps of establishing the temperature and humidity prediction model in the upper computer are as follows:
step 1, collecting historical data of temperature and humidity in a greenhouse;
step 2, performing data preprocessing on the collected historical data to construct a training data set and a test data set for predicting the temperature and humidity;
step 3, training the training data set through a machine learning algorithm to obtain a prediction model; and testing the prediction model by using the test data set, and outputting a corresponding confidence coefficient.
3. The machine learning-based greenhouse temperature and humidity monitoring and adaptive adjustment system according to claim 2, wherein in the step 2, the data preprocessing mainly comprises data cleaning and data standardization.
4. The machine learning-based greenhouse temperature and humidity monitoring and adaptive adjusting system according to claim 2, wherein in step 3, the machine learning algorithm is a ridge regression algorithm in linear regression.
CN202110496029.3A 2021-05-07 2021-05-07 Greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning Pending CN113157030A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110496029.3A CN113157030A (en) 2021-05-07 2021-05-07 Greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110496029.3A CN113157030A (en) 2021-05-07 2021-05-07 Greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning

Publications (1)

Publication Number Publication Date
CN113157030A true CN113157030A (en) 2021-07-23

Family

ID=76873698

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110496029.3A Pending CN113157030A (en) 2021-05-07 2021-05-07 Greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning

Country Status (1)

Country Link
CN (1) CN113157030A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113849023A (en) * 2021-09-23 2021-12-28 国电南瑞科技股份有限公司 Logic method for regulating and controlling environment in offshore wind power converter cabinet
CN114878788A (en) * 2022-06-14 2022-08-09 古田县恒春农业开发有限公司 Flower planting intelligence humidity detection device
CN115419120A (en) * 2022-06-08 2022-12-02 山东大学 Highway subgrade settlement monitoring and predicting method
CN117391482A (en) * 2023-12-12 2024-01-12 河北省农林科学院 Greenhouse temperature intelligent early warning method and system based on big data monitoring

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130093592A1 (en) * 2011-10-14 2013-04-18 Zehua Lan Internet of Things Based Farm Greenhouse Monitor and Alarm Management System
CN104166417A (en) * 2014-08-08 2014-11-26 洛阳理工学院 Temperature and humidity control system convenient to monitor in real time and suitable for greenhouse
CN109213240A (en) * 2018-10-19 2019-01-15 齐鲁工业大学 A kind of strawberry greenhouse wireless monitor and control system based on self adaptive control
CN208705751U (en) * 2018-10-09 2019-04-05 四川省农业科学院服务中心 Agricultural greenhouse greenhouse-environment data acquisition device based on WIFI
CN112418498A (en) * 2020-11-12 2021-02-26 中国农业大学 Temperature prediction method and system for intelligent greenhouse

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130093592A1 (en) * 2011-10-14 2013-04-18 Zehua Lan Internet of Things Based Farm Greenhouse Monitor and Alarm Management System
CN104166417A (en) * 2014-08-08 2014-11-26 洛阳理工学院 Temperature and humidity control system convenient to monitor in real time and suitable for greenhouse
CN208705751U (en) * 2018-10-09 2019-04-05 四川省农业科学院服务中心 Agricultural greenhouse greenhouse-environment data acquisition device based on WIFI
CN109213240A (en) * 2018-10-19 2019-01-15 齐鲁工业大学 A kind of strawberry greenhouse wireless monitor and control system based on self adaptive control
CN112418498A (en) * 2020-11-12 2021-02-26 中国农业大学 Temperature prediction method and system for intelligent greenhouse

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113849023A (en) * 2021-09-23 2021-12-28 国电南瑞科技股份有限公司 Logic method for regulating and controlling environment in offshore wind power converter cabinet
CN113849023B (en) * 2021-09-23 2022-06-07 国电南瑞科技股份有限公司 Logic method for regulating and controlling environment in offshore wind power converter cabinet
CN115419120A (en) * 2022-06-08 2022-12-02 山东大学 Highway subgrade settlement monitoring and predicting method
CN114878788A (en) * 2022-06-14 2022-08-09 古田县恒春农业开发有限公司 Flower planting intelligence humidity detection device
CN117391482A (en) * 2023-12-12 2024-01-12 河北省农林科学院 Greenhouse temperature intelligent early warning method and system based on big data monitoring
CN117391482B (en) * 2023-12-12 2024-02-09 河北省农林科学院 Greenhouse temperature intelligent early warning method and system based on big data monitoring

Similar Documents

Publication Publication Date Title
CN113157030A (en) Greenhouse temperature and humidity monitoring and self-adaptive adjusting system based on machine learning
US20240000046A1 (en) Predictive control system and regulatory method for temperature of livestock house
CN106873676A (en) A kind of wisdom agricultural data acquisition method and system based on Internet of Things
CN205455083U (en) Novel intelligence water -saving irrigation automatic control system
CN205692080U (en) Breeding environment monitor control system based on Internet of Things
CN103235579A (en) Network-based self-adaptive control system for greenhouses of facility agriculture
CN205284410U (en) Intelligent terminal control's big -arch shelter greenhouse system
CN201194078Y (en) Greenhouse control apparatus based on microcontroller
CN112465109A (en) Green house controlling means based on cloud limit is in coordination
CN116301138B (en) Intelligent supervision system of agricultural greenhouse based on sunlight greenhouse
KR20210077421A (en) Ventilation control system by automatic for greenhouse in Smart farm
CN116360331A (en) Universal automatic control system and control method
CN109213240A (en) A kind of strawberry greenhouse wireless monitor and control system based on self adaptive control
CN116649160A (en) Edible fungus strain production monitoring system and monitoring method
CN109116827B (en) Solar greenhouse water and fertilizer integrated irrigation control method and device based on Internet of things
CN112181032B (en) Intelligent pasture environment control system
CN114115403A (en) Broiler chicken breeding environment intelligent control device raises in cages
CN111090291A (en) Warmhouse booth intelligence control system
CN206258754U (en) A kind of greenhouse intelligent control system
CN117391482A (en) Greenhouse temperature intelligent early warning method and system based on big data monitoring
CN111061323A (en) Intelligent temperature and humidity control system of greenhouse
CN205038459U (en) Environment regulation and control system of pouity dwelling place
CN103558888B (en) Cowshed Intelligent environment control system and control method
CN114190203B (en) Internet of things agricultural greenhouse temperature control device and method
CN110865668A (en) Remote monitoring and intelligent decision-making system for facility gardening

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210723