CN113240152A - Environment monitoring method, equipment and medium for live poultry feeding of intelligent cage - Google Patents
Environment monitoring method, equipment and medium for live poultry feeding of intelligent cage Download PDFInfo
- Publication number
- CN113240152A CN113240152A CN202110342728.2A CN202110342728A CN113240152A CN 113240152 A CN113240152 A CN 113240152A CN 202110342728 A CN202110342728 A CN 202110342728A CN 113240152 A CN113240152 A CN 113240152A
- Authority
- CN
- China
- Prior art keywords
- value
- environmental parameter
- cage
- alarm
- normal
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 244000144977 poultry Species 0.000 title claims abstract description 28
- 238000012544 monitoring process Methods 0.000 title claims abstract description 27
- 230000007613 environmental effect Effects 0.000 claims abstract description 125
- 230000008859 change Effects 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000012806 monitoring device Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 abstract description 32
- 239000007789 gas Substances 0.000 description 43
- 229910021529 ammonia Inorganic materials 0.000 description 10
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 244000144972 livestock Species 0.000 description 5
- 230000000306 recurrent effect Effects 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000009395 breeding Methods 0.000 description 3
- 230000001488 breeding effect Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 241000287828 Gallus gallus Species 0.000 description 1
- 241000282414 Homo sapiens Species 0.000 description 1
- 239000003570 air Substances 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 229910000037 hydrogen sulfide Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000010871 livestock manure Substances 0.000 description 1
- 229910000069 nitrogen hydride Inorganic materials 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 150000007524 organic acids Chemical class 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Primary Health Care (AREA)
- Housing For Livestock And Birds (AREA)
Abstract
The invention relates to the technical field of cage environment monitoring, in particular to an environment monitoring method, equipment and medium for live poultry feeding of an intelligent cage, wherein the method comprises the following steps: acquiring a first environment parameter in the cage and a second environment parameter outside the cage which are sent by an internal sensor and an external sensor of the cage; judging whether the first environmental parameter and the second environmental parameter are normal or not; when the first environmental parameter and the second environmental parameter are normal, inputting the first environmental parameter and the second environmental parameter into a preset concentration prediction model of target gas; the concentration prediction model of the target gas predicts the concentration change value of the target gas according to the normal first environmental parameter and the normal second environmental parameter; and when the concentration change value of the predicted target gas exceeds a preset value, controlling an alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to a user terminal. According to the technical scheme provided by the invention, the ammonia gas concentration in the cage can be predicted.
Description
Technical Field
The invention relates to the technical field of cage environment monitoring, in particular to an environment monitoring method, equipment and medium for live poultry feeding of an intelligent cage.
Background
Along with intensive and large-scale development of livestock and poultry breeding, the problem of malodorous gas pollution is increasingly obvious, and ammonia gas is one of main sources of malodorous gas in cages. The bad smell generated by the livestock and poultry breeding not only causes serious pollution to the air, soil and water, but also greatly influences the living quality and the body health of human beings. The malodorous gas in the livestock and poultry house is mainly generated by fermenting and decomposing chicken manure and wastes and releases a large amount of odorous harmful gases such as ammonia gas, hydrogen sulfide, methane, organic acid and the like, wherein the ammonia gas is the most main malodorous gas in the laying hen production environment and is the gas which has the greatest influence on the environment and the body health. Ammonia (NH3) not only causes great pollution to the environment, but also seriously affects the health of livestock and poultry, induces various diseases, causes the reduction of production performance, and seriously restricts the sustainable development of livestock and poultry breeding in China due to ammonia emission pollution.
The method for predicting the ammonia concentration in the cage is researched, so that the concentration change of the ammonia in the cage can be known in advance by production departments, measures can be taken in advance to reduce the ammonia concentration in the cage, and the pollution of the ammonia emission in the cage to the environment is reduced.
Therefore, there is a need for an environmental monitoring method, apparatus and medium for live bird feeding in intelligent cages, so as to be able to predict the ammonia gas concentration in the cages.
Disclosure of Invention
The invention mainly aims to provide an environment monitoring method, equipment and medium for live poultry feeding of an intelligent cage, so that the ammonia gas concentration of the cage can be predicted.
To achieve the above object, a first aspect of the present invention provides an environmental monitoring method for live poultry feeding in an intelligent cage, the method comprising:
acquiring a first environment parameter in the cage and a second environment parameter outside the cage which are sent by an internal sensor and an external sensor of the cage;
judging whether the first environmental parameter and the second environmental parameter are normal or not;
when the first environmental parameter and the second environmental parameter are normal, inputting the first environmental parameter and the second environmental parameter into a preset concentration prediction model of target gas;
the concentration prediction model of the target gas predicts the concentration change value of the target gas according to the normal first environmental parameter and the normal second environmental parameter;
and when the concentration change value of the predicted target gas exceeds a preset value, controlling an alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to a user terminal.
In some possible embodiments, the method further comprises:
training the concentration prediction model; wherein the concentration prediction model is an LSTM model;
inputting the normal first environmental parameters and the normal second environmental parameters into the concentration prediction model and obtaining predicted values after a period of time t;
comparing the predicted value with a real value after a period of time t, and if the difference value between the predicted value and the real value is greater than a preset threshold value, recording the prediction failure times, modifying the setting parameters of the LSTM model and re-training; if the difference value between the predicted value and the true value is less than or equal to a preset threshold value, recording the number of successful prediction times;
and when the proportion of the prediction failure times in the prediction times is less than or equal to 15%, the training is successful.
In some possible embodiments, the determining whether the first environmental parameter and the second environmental parameter are normal specifically includes:
judging whether the first environmental parameter and the second environmental parameter are normal or not according to a formula I;
|xn-x' | > 3 σ wherein,
when x isnX' is greater than three times σ in absolute value of the difference with xnIs replaced by
In some possible embodiments, the determining whether the first environmental parameter and the second environmental parameter are normal further includes:
by the formula two pairs xnCarrying out average processing according to hours, and carrying out normalization processing on the data after the average processing through a formula III;
x*＝(xn-xmin)/(xmax-xmin) Formula three
Wherein x isnCollecting values for the sensors; x' is the mean of the sensor data sequence; x is the number ofn’The data value after abnormal data processing; σ is the standard deviation of the sensor data sequence; n is a data point; x is the number ofhThe values are averaged in hours; t is a sensor acquisition time interval; x is the number ofmaxIs the maximum value of the sensor data sequence; x is the number ofminIs the minimum of the sensor data sequence; x is the number of*Is normalized.
In some possible embodiments, the method further comprises:
the input parameters of the LSTM model are set as the normal first environmental parameters and the normal second environmental parameters, the time step of an input layer is set as 1, and the number of hidden layers is set as 50; the number of output variables is set to 1 and the maximum number of iterations is 2000.
In some possible embodiments, when the predicted change value of the concentration of the target gas exceeds a preset value, the controlling the alarm to generate an alarm signal and generate an alarm interface to transmit to the user terminal specifically includes:
when at t1When the concentration change value of the predicted target gas exceeds a preset value, the number is recorded as 1;
when at t2When the concentration change value of the predicted target gas exceeds a preset value, counting by + 1;
and if the count exceeds the preset value in the preset time period, controlling the alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to the user terminal.
In some possible embodiments, when the predicted change value of the concentration of the target gas exceeds a preset value, the method for controlling the alarm to generate an alarm signal and generating an alarm interface to transmit the alarm interface to the user terminal specifically further includes:
if the count does not exceed the preset value within the preset time period, judging whether the count exceeds a reminding threshold value;
and when the count exceeds the reminding threshold, generating a reminding interface and transmitting the reminding interface to the user terminal.
In some possible embodiments, when the predicted change value of the concentration of the target gas exceeds a preset value, the method for controlling the alarm to generate an alarm signal and generating an alarm interface to transmit the alarm interface to the user terminal specifically further includes:
and when the count exceeds the reminding threshold, recording the time point exceeding the reminding threshold and transmitting the time point to the user terminal.
The invention discloses in a second aspect an environment monitoring device for live poultry feeding in an intelligent cage, which is characterized by comprising:
a parameter acquisition module: the system comprises a cage internal sensor, a cage external sensor, a cage internal sensor and a cage external sensor, wherein the cage internal sensor and the cage external sensor are used for acquiring a first environment parameter in the cage and a second environment parameter outside the cage;
a judging module: the environment monitoring system is used for judging whether the first environment parameter and the second environment parameter are normal or not;
an input module: the concentration prediction model is used for inputting the first environmental parameter and the second environmental parameter into a preset target gas concentration prediction model when the first environmental parameter and the second environmental parameter are normal;
a prediction module: the concentration prediction model of the target gas predicts the concentration change value of the target gas according to the normal first environmental parameter and the normal second environmental parameter;
the control alarm module: and when the concentration change value of the predicted target gas exceeds a preset value, controlling an alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to the user terminal.
In a third aspect, the invention discloses a storage medium, wherein the storage medium stores an executable program, and when the executable program is executed, the environment monitoring method for feeding live poultry in the intelligent cage is realized.
The technical scheme provided by the invention has the following advantages:
obtaining a first environment parameter in the house and a second environment parameter outside the house which are sent by an internal sensor and an external sensor of the cage; judging whether the first environmental parameter and the second environmental parameter are normal or not; when the first environmental parameter and the second environmental parameter are normal, inputting the first environmental parameter and the second environmental parameter into a preset concentration prediction model of target gas; the concentration prediction model of the target gas predicts the concentration change value of the target gas according to the normal first environmental parameter and the normal second environmental parameter; and when the concentration change value of the predicted target gas exceeds a preset value, controlling an alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to a user terminal. Thereby, the ammonia gas concentration in the cage can be predicted.
Drawings
Fig. 1 is a schematic flow chart of an environment monitoring method for live poultry feeding in an intelligent cage according to an embodiment of the present invention.
Fig. 2 is a schematic view of a scene of an environment monitoring method for live poultry feeding in an intelligent cage according to another embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an environment monitoring device for live poultry feeding in an intelligent cage according to an embodiment of the present invention.
Fig. 4 is a block diagram of a server according to another embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 and 2, in one aspect, the present invention provides an environment monitoring method for live poultry feeding in an intelligent cage, applied to a sensor, a server and a user terminal, the method comprising:
step S10: acquiring a first environment parameter in the house and a second environment parameter outside the house sent by the sensors inside and outside the cage.
In some possible embodiments, the sensors inside the cage comprise three sensors of temperature, humidity and illumination, and the sensors outside the cage comprise a plurality of sensors of meteorological temperature, humidity, wind speed, wind direction, atmospheric pressure, rainfall, solar radiation and the like.
Step S20: and judging whether the first environmental parameter and the second environmental parameter are normal or not.
In some possible embodiments, after receiving the first environmental parameter and the second environmental parameter, the server further determines whether the first environmental parameter and the second environmental parameter are normal, and performs preliminary screening.
The primary screening method comprises the following steps:
|xn-x' | > 3 σ wherein,
when x isnX' is greater than three times σ in absolute value of the difference with xnIs replaced by
That is, when xnX' is greater than three times σ in absolute value of the difference with xnIs replaced by
By the formula two pairs xnAveraging according to hours, and then carrying out average processing on the data by a formula IIINormalization processing;
x*＝(xn-xmin)/(xmax-xmin) Formula three
Wherein x isnCollecting values for the sensors; x' is the mean of the sensor data sequence; x is the number ofn’The data value after abnormal data processing; σ is the standard deviation of the sensor data sequence; n is a data point; x is the number ofhThe values are averaged in hours; t is a sensor acquisition time interval; x is the number ofmaxIs the maximum value of the sensor data sequence; x is the number ofminIs the minimum of the sensor data sequence; x is the number of*Is normalized. Thus ensuring the accuracy of the data transmitted from the sensors inside and outside the cage.
Step S30: and when the first environmental parameter and the second environmental parameter are normal, inputting the first environmental parameter and the second environmental parameter into a preset concentration prediction model of the target gas.
Training the concentration prediction model; wherein the concentration prediction model is an LSTM model; the input parameters of the LSTM model are set as the normal first environmental parameters and the normal second environmental parameters, the time step of an input layer is set as 1, and the number of hidden layers is set as 50; the number of output variables is set to 1 and the maximum number of iterations is 2000.
A Recurrent Neural Network (RNN) is a Neural Network with a feedback structure whose inputs are not only related to the Network weights of the current inputs, but also to previous Network inputs. The RNN algorithm can take into account timing dependencies and is well suited to processing sequence data. The ammonia gas concentration of the cage can be predicted by adopting an RNN algorithm, but the method has the problem of gradient disappearance. In order to solve the problem, an input gate, a forgetting gate and an output gate are added on the basis of the recurrent neural network to respectively control the input and output of information flow and the state of a cell unit, so that the update of control information on the state of the cell is realized.
And inputting the normal first environmental parameters and the normal second environmental parameters into the concentration prediction model and obtaining predicted values after a period of time t.
Comparing the predicted value with a real value after a period of time t, and if the difference value between the predicted value and the real value is greater than a preset threshold value, recording the prediction failure times, modifying the setting parameters of the LSTM model and re-training; and if the difference value between the predicted value and the true value is less than or equal to a preset threshold value, recording the number of successful prediction times.
And when the proportion of the prediction failure times in the prediction times is less than or equal to 15%, the training is successful.
Of course, the first environmental parameter and the second environmental parameter may also be filtered; specifically, an importance selection is carried out on environmental variables influencing the change of the henhouse ammonia concentration by using a random forest algorithm, and then the screened environmental variables are input into an LSTM henhouse ammonia concentration prediction model.
Step S40: and the concentration prediction model of the target gas predicts the concentration change value of the target gas according to the normal first environmental parameter and the normal second environmental parameter.
Step S50: and when the concentration change value of the predicted target gas exceeds a preset value, controlling an alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to a user terminal.
When at t1When the concentration change value of the predicted target gas exceeds a preset value, the number is recorded as 1;
when at t2When the concentration change value of the predicted target gas exceeds a preset value, counting by + 1;
and if the count exceeds the preset value in the preset time period, controlling the alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to the user terminal.
If the count does not exceed the preset value within the preset time period, judging whether the count exceeds a reminding threshold value;
and when the count exceeds the reminding threshold, generating a reminding interface and transmitting the reminding interface to the user terminal.
And when the count exceeds the reminding threshold, recording the time point exceeding the reminding threshold and transmitting the time point to the user terminal.
The value of the reminding threshold is smaller than that of the preset value (trigger alarm signal), so that gradient alarm is realized, alarm is performed when the alarm threshold is reached, and reminding is performed when the reminding threshold is reached, so that more refined reminding is realized, and periodic monitoring is guaranteed. Of course, the alarm can also adopt the function of dialing a telephone by adopting an audible and visual alarm or a GSM module.
Referring to fig. 3, the present application also provides an environment monitoring apparatus for live poultry feeding in an intelligent cage, the apparatus comprising:
the parameter acquisition module 10: the system comprises a cage internal sensor, a cage external sensor, a cage internal sensor and a cage external sensor, wherein the cage internal sensor and the cage external sensor are used for acquiring a first environment parameter in the cage and a second environment parameter outside the cage;
the judging module 20: the environment monitoring system is used for judging whether the first environment parameter and the second environment parameter are normal or not;
the input module 30: the concentration prediction model is used for inputting the first environmental parameter and the second environmental parameter into a preset target gas concentration prediction model when the first environmental parameter and the second environmental parameter are normal;
the prediction module 40: the concentration prediction model of the target gas predicts the concentration change value of the target gas according to the normal first environmental parameter and the normal second environmental parameter;
the control alarm module 50: and when the concentration change value of the predicted target gas exceeds a preset value, controlling an alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to the user terminal.
Referring to fig. 4, the present application further provides a server 30, which can be applied to a sensor, a server, and a user side, wherein the server 30 includes a memory 301 and a processor 302, wherein the memory 301 and the processor 302 are electrically connected through a bus 303.
The memory 301 includes at least one type of readable storage medium, which includes flash memory, hard disk, multi-media card, card type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, and the like. The memory 301 may in some embodiments be an internal storage unit of the server 30, such as a hard disk of the server 30. The memory 301 may also be an external storage device of the server 30 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the server 30. The memory 301 may be used not only for storing application software installed in the vehicle-mounted device and various types of data, such as codes of computer-readable programs, etc., but also for temporarily storing data that has been output or will be output, i.e., the first memory may be used as a storage medium storing a computer-executable environment monitoring program for live poultry feeding in the intelligent cage.
The processor 302 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip in some embodiments, and the processor 302 may call the environment monitoring program for live poultry feeding in the intelligent cage stored in the memory 301 to implement the following steps:
step S10: acquiring a first environment parameter in the house and a second environment parameter outside the house sent by the sensors inside and outside the cage.
In some possible embodiments, the sensors inside the cage comprise three sensors of temperature, humidity and illumination, and the sensors outside the cage comprise a plurality of sensors of meteorological temperature, humidity, wind speed, wind direction, atmospheric pressure, rainfall, solar radiation and the like.
Step S20: and judging whether the first environmental parameter and the second environmental parameter are normal or not.
In some possible embodiments, after receiving the first environmental parameter and the second environmental parameter, the server further determines whether the first environmental parameter and the second environmental parameter are normal, and performs preliminary screening.
The primary screening method comprises the following steps:
|xn-x' | > 3 σ wherein,
when x isnX' is greater than three times σ in absolute value of the difference with xnIs replaced by
That is, when xnX' is greater than three times σ in absolute value of the difference with xnIs replaced by
By the formula two pairs xnCarrying out average processing according to hours, and carrying out normalization processing on the data after the average processing through a formula III;
x*＝(xn-xmin)/(xmax-xmin) Formula three
Wherein x isnCollecting values for the sensors; x' is the mean of the sensor data sequence; x is the number ofn’The data value after abnormal data processing; σ is the standard deviation of the sensor data sequence; n is a data point; x is the number ofhThe values are averaged in hours; t is a sensor acquisition time interval; x is the number ofmaxIs the maximum value of the sensor data sequence; x is the number ofminIs the minimum of the sensor data sequence; x is the number of*Is normalized. Thus ensuring the accuracy of the data transmitted from the sensors inside and outside the cage.
Step S30: and when the first environmental parameter and the second environmental parameter are normal, inputting the first environmental parameter and the second environmental parameter into a preset concentration prediction model of the target gas.
Training the concentration prediction model; wherein the concentration prediction model is an LSTM model; the input parameters of the LSTM model are set as the normal first environmental parameters and the normal second environmental parameters, the time step of an input layer is set as 1, and the number of hidden layers is set as 50; the number of output variables is set to 1 and the maximum number of iterations is 2000.
A Recurrent Neural Network (RNN) is a Neural Network with a feedback structure whose inputs are not only related to the Network weights of the current inputs, but also to previous Network inputs. The RNN algorithm can take into account timing dependencies and is well suited to processing sequence data. The ammonia gas concentration of the cage can be predicted by adopting an RNN algorithm, but the method has the problem of gradient disappearance. In order to solve the problem, an input gate, a forgetting gate and an output gate are added on the basis of the recurrent neural network to respectively control the input and output of information flow and the state of a cell unit, so that the update of control information on the state of the cell is realized.
And inputting the normal first environmental parameters and the normal second environmental parameters into the concentration prediction model and obtaining predicted values after a period of time t.
Comparing the predicted value with a real value after a period of time t, and if the difference value between the predicted value and the real value is greater than a preset threshold value, recording the prediction failure times, modifying the setting parameters of the LSTM model and re-training; and if the difference value between the predicted value and the true value is less than or equal to a preset threshold value, recording the number of successful prediction times.
And when the proportion of the prediction failure times in the prediction times is less than or equal to 15%, the training is successful.
Of course, the first environmental parameter and the second environmental parameter may also be filtered; specifically, an importance selection is carried out on environmental variables influencing the change of the henhouse ammonia concentration by using a random forest algorithm, and then the screened environmental variables are input into an LSTM henhouse ammonia concentration prediction model.
Step S40: and the concentration prediction model of the target gas predicts the concentration change value of the target gas according to the normal first environmental parameter and the normal second environmental parameter.
Step S50: and when the concentration change value of the predicted target gas exceeds a preset value, controlling an alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to a user terminal.
When at t1When the concentration change value of the predicted target gas exceeds a preset value, the number is recorded as 1;
when at t2When the concentration change value of the predicted target gas exceeds a preset value, counting by + 1;
and if the count exceeds the preset value in the preset time period, controlling the alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to the user terminal.
If the count does not exceed the preset value within the preset time period, judging whether the count exceeds a reminding threshold value;
and when the count exceeds the reminding threshold, generating a reminding interface and transmitting the reminding interface to the user terminal.
And when the count exceeds the reminding threshold, recording the time point exceeding the reminding threshold and transmitting the time point to the user terminal.
The value of the reminding threshold is smaller than that of the preset value (trigger alarm signal), so that gradient alarm is realized, alarm is performed when the alarm threshold is reached, and reminding is performed when the reminding threshold is reached, so that more refined reminding is realized, and periodic monitoring is guaranteed. Of course, the alarm can also adopt the function of dialing a telephone by adopting an audible and visual alarm or a GSM module.
The technical scheme provided by the invention has the following advantages:
obtaining a first environment parameter in the house and a second environment parameter outside the house which are sent by an internal sensor and an external sensor of the cage; judging whether the first environmental parameter and the second environmental parameter are normal or not; when the first environmental parameter and the second environmental parameter are normal, inputting the first environmental parameter and the second environmental parameter into a preset concentration prediction model of target gas; the concentration prediction model of the target gas predicts the concentration change value of the target gas according to the normal first environmental parameter and the normal second environmental parameter; and when the concentration change value of the predicted target gas exceeds a preset value, controlling an alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to a user terminal. Thereby, the ammonia gas concentration in the cage can be predicted.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An environmental monitoring method for live poultry feeding in an intelligent cage, the method comprising:
acquiring a first environment parameter in the cage and a second environment parameter outside the cage which are sent by an internal sensor and an external sensor of the cage;
judging whether the first environmental parameter and the second environmental parameter are normal or not;
when the first environmental parameter and the second environmental parameter are normal, inputting the first environmental parameter and the second environmental parameter into a preset concentration prediction model of target gas;
the concentration prediction model of the target gas predicts the concentration change value of the target gas according to the normal first environmental parameter and the normal second environmental parameter;
and when the concentration change value of the predicted target gas exceeds a preset value, controlling an alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to a user terminal.
2. The method for environmental monitoring of live poultry feeding in an intelligent cage according to claim 1, wherein the method further comprises:
training the concentration prediction model; wherein the concentration prediction model is an LSTM model;
inputting the normal first environmental parameters and the normal second environmental parameters into the concentration prediction model and obtaining predicted values after a period of time t;
comparing the predicted value with a real value after a period of time t, and if the difference value between the predicted value and the real value is greater than a preset threshold value, recording the prediction failure times, modifying the setting parameters of the LSTM model and re-training; if the difference value between the predicted value and the true value is less than or equal to a preset threshold value, recording the number of successful prediction times;
and when the proportion of the prediction failure times in the prediction times is less than or equal to 15%, the training is successful.
3. The method for monitoring the environment for feeding live poultry in an intelligent cage according to claim 2, wherein the determining whether the first environmental parameter and the second environmental parameter are normal comprises:
judging whether the first environmental parameter and the second environmental parameter are normal or not according to a formula I;
|xn-x' | > 3 σ wherein,
when x isnX' is greater than three times σ in absolute value of the difference with xnIs replaced by
4. The method of claim 3, wherein said determining whether said first environmental parameter and said second environmental parameter are normal further comprises:
by the formula two pairs xnCarrying out average processing according to hours, and carrying out normalization processing on the data after the average processing through a formula III;
x*＝(xn-xmin)/(xmax-xmin) Formula three
Wherein x isnCollecting values for the sensors;x' is the mean of the sensor data sequence; x is the number ofn’The data value after abnormal data processing; σ is the standard deviation of the sensor data sequence; n is a data point; x is the number ofhThe values are averaged in hours; t is a sensor acquisition time interval; x is the number ofmaxIs the maximum value of the sensor data sequence; x is the number ofminIs the minimum of the sensor data sequence; x is the number of*Is normalized.
5. The method for environmental monitoring of live poultry feeding in an intelligent cage according to claim 4, wherein the method further comprises:
the input parameters of the LSTM model are set as the normal first environmental parameters and the normal second environmental parameters, the time step of an input layer is set as 1, and the number of hidden layers is set as 50; the number of output variables is set to 1 and the maximum number of iterations is 2000.
6. The method for monitoring the environment for feeding live poultry in an intelligent cage according to claim 1, wherein the step of controlling an alarm to generate an alarm signal and generate an alarm interface to transmit the alarm interface to a user terminal when the concentration variation value of the predicted target gas exceeds a preset value specifically comprises the steps of:
when at t1When the concentration change value of the predicted target gas exceeds a preset value, the number is recorded as 1;
when at t2When the concentration change value of the predicted target gas exceeds a preset value, counting by + 1;
and if the count exceeds the preset value in the preset time period, controlling the alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to the user terminal.
7. The method for monitoring the environment for feeding live poultry in an intelligent cage according to claim 6, wherein when the concentration variation value of the predicted target gas exceeds a preset value, the alarm is controlled to generate an alarm signal and generate an alarm interface to be transmitted to the user terminal, and the method further comprises:
if the count does not exceed the preset value within the preset time period, judging whether the count exceeds a reminding threshold value;
and when the count exceeds the reminding threshold, generating a reminding interface and transmitting the reminding interface to the user terminal.
8. The method for monitoring the feeding environment of live poultry in an intelligent cage according to claim 7, wherein when the concentration variation value of the predicted target gas exceeds a preset value, the alarm is controlled to generate an alarm signal and generate an alarm interface to be transmitted to the user terminal, and the method further comprises:
and when the count exceeds the reminding threshold, recording the time point exceeding the reminding threshold and transmitting the time point to the user terminal.
9. An environmental monitoring device for live bird feeding in an intelligent cage, the device comprising:
a parameter acquisition module: the system comprises a cage internal sensor, a cage external sensor, a cage internal sensor and a cage external sensor, wherein the cage internal sensor and the cage external sensor are used for acquiring a first environment parameter in the cage and a second environment parameter outside the cage;
a judging module: the environment monitoring system is used for judging whether the first environment parameter and the second environment parameter are normal or not;
an input module: the concentration prediction model is used for inputting the first environmental parameter and the second environmental parameter into a preset target gas concentration prediction model when the first environmental parameter and the second environmental parameter are normal;
a prediction module: the concentration prediction model of the target gas predicts the concentration change value of the target gas according to the normal first environmental parameter and the normal second environmental parameter;
the control alarm module: and when the concentration change value of the predicted target gas exceeds a preset value, controlling an alarm to generate an alarm signal, generating an alarm interface and transmitting the alarm interface to the user terminal.
10. A medium, characterized in that it stores an executable program that, when executed, implements the method for environmental monitoring of live poultry feeding of an intelligent cage according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110342728.2A CN113240152A (en) | 2021-03-30 | 2021-03-30 | Environment monitoring method, equipment and medium for live poultry feeding of intelligent cage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110342728.2A CN113240152A (en) | 2021-03-30 | 2021-03-30 | Environment monitoring method, equipment and medium for live poultry feeding of intelligent cage |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113240152A true CN113240152A (en) | 2021-08-10 |
Family
ID=77130844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110342728.2A Pending CN113240152A (en) | 2021-03-30 | 2021-03-30 | Environment monitoring method, equipment and medium for live poultry feeding of intelligent cage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113240152A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114486656A (en) * | 2021-12-31 | 2022-05-13 | 扬州江净空调制造有限公司 | Dynamic environment monitoring system for medical clean room |
| CN117111560A (en) * | 2023-09-01 | 2023-11-24 | 廊坊市珍圭谷科技有限公司 | Environment monitoring method and system for manufacturing workshop |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080464A (en) * | 2019-11-27 | 2020-04-28 | 中国农业大学 | Pond culture water quality key factor prediction method and device |
| CN111368975A (en) * | 2020-02-25 | 2020-07-03 | 东北农业大学 | Method for predicting dynamic change of multi-environment factors in pigsty |
| CN112130596A (en) * | 2020-09-25 | 2020-12-25 | 创新奇智(青岛)科技有限公司 | Farm environment adjusting method and device, electronic equipment and readable storage medium |
-
2021
- 2021-03-30 CN CN202110342728.2A patent/CN113240152A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080464A (en) * | 2019-11-27 | 2020-04-28 | 中国农业大学 | Pond culture water quality key factor prediction method and device |
| CN111368975A (en) * | 2020-02-25 | 2020-07-03 | 东北农业大学 | Method for predicting dynamic change of multi-environment factors in pigsty |
| CN112130596A (en) * | 2020-09-25 | 2020-12-25 | 创新奇智(青岛)科技有限公司 | Farm environment adjusting method and device, electronic equipment and readable storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114486656A (en) * | 2021-12-31 | 2022-05-13 | 扬州江净空调制造有限公司 | Dynamic environment monitoring system for medical clean room |
| CN114486656B (en) * | 2021-12-31 | 2022-12-02 | 扬州江净空调制造有限公司 | Dynamic environment monitoring system for medical clean room |
| CN117111560A (en) * | 2023-09-01 | 2023-11-24 | 廊坊市珍圭谷科技有限公司 | Environment monitoring method and system for manufacturing workshop |
| CN117111560B (en) * | 2023-09-01 | 2024-05-24 | 廊坊市珍圭谷科技股份有限公司 | Environment monitoring method and system for manufacturing workshop |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10552762B2 (en) | Machine learning of physical conditions based on abstract relations and sparse labels | |
| CN113240152A (en) | Environment monitoring method, equipment and medium for live poultry feeding of intelligent cage | |
| CN107567083B (en) | Method and device for performing power-saving optimization processing | |
| CN109636826A (en) | Live pig weight method for measurement, server and computer readable storage medium | |
| CN109345798B (en) | Farm monitoring method, device, equipment and storage medium | |
| CN113642263B (en) | Air quality early warning method and device based on Beidou grid | |
| CN113342098A (en) | Multipurpose farm environment intelligent control method and system | |
| CN111210128A (en) | Wetland early warning method based on artificial intelligence and random self-adaptive threshold | |
| CN111011247A (en) | Sustainable and intelligent pig raising method | |
| CN107632132A (en) | A kind of water quality monitoring warning system with forecast function | |
| CN112216351A (en) | Desulfurization optimization method and device, electronic equipment and storage medium | |
| CN115457468A (en) | Intelligent livestock monitoring method and system for large grassland | |
| Wu | Crop growth monitoring system based on agricultural internet of things technology | |
| CN117077854B (en) | Building energy consumption monitoring method and system based on sensor network | |
| US20160025530A1 (en) | Sonde | |
| CN109359624B (en) | Neural network-based prediction method and prediction device for feeding behavior of laying hens | |
| CN116307879A (en) | Efficient cultivation method, system and medium for penaeus monodon larvae | |
| CN116090902A (en) | Remote farmland monitoring method and system | |
| CN110955286B (en) | Poultry egg monitoring method and device | |
| CN107830641B (en) | Heat treatment method and apparatus | |
| CN116011896A (en) | Method and system for monitoring, preventing and controlling ecological area | |
| CN114330858A (en) | Evaluation system of water ecological environment | |
| KR20210062238A (en) | Method for Image Information Analysis Based Prevention System and Method thereof | |
| CN111090707B (en) | Data processing method and device, electronic equipment and storage medium | |
| Vignesh et al. | Deep Reinforcement Learning Based Weather Monitoring Systemusing Arduino for Smart Environment |
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 | ||
| CB02 | Change of applicant information |
Address after: Room 238, room 406, 1 Yichuang street, Huangpu District, Guangzhou, Guangdong 510700 Applicant after: Guangzhou langguo Electronic Technology Co.,Ltd. Address before: Room 238, room 406, 1 Yichuang street, Huangpu District, Guangzhou, Guangdong 510700 Applicant before: GUANGZHOU LANGO ELECTRONIC SCIENCE & TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210810 |
|
| RJ01 | Rejection of invention patent application after publication |