CN113642729A - Intelligent biogas slurry application method and system based on machine learning and storage medium - Google Patents
Intelligent biogas slurry application method and system based on machine learning and storage medium Download PDFInfo
- Publication number
- CN113642729A CN113642729A CN202110986629.8A CN202110986629A CN113642729A CN 113642729 A CN113642729 A CN 113642729A CN 202110986629 A CN202110986629 A CN 202110986629A CN 113642729 A CN113642729 A CN 113642729A
- Authority
- CN
- China
- Prior art keywords
- biogas slurry
- application
- slurry application
- farmland
- data
- 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
- 239000002002 slurry Substances 0.000 title claims abstract description 152
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000010801 machine learning Methods 0.000 title claims abstract description 25
- 238000003860 storage Methods 0.000 title claims description 9
- 238000012549 training Methods 0.000 claims abstract description 29
- 238000013145 classification model Methods 0.000 claims abstract description 23
- 238000003973 irrigation Methods 0.000 claims abstract description 14
- 230000002262 irrigation Effects 0.000 claims abstract description 14
- 230000012010 growth Effects 0.000 claims abstract description 10
- 239000002689 soil Substances 0.000 claims description 44
- 238000013528 artificial neural network Methods 0.000 claims description 26
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 21
- 239000003337 fertilizer Substances 0.000 claims description 12
- 235000021049 nutrient content Nutrition 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 8
- 238000011478 gradient descent method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 235000015097 nutrients Nutrition 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 238000002156 mixing Methods 0.000 description 11
- 238000003756 stirring Methods 0.000 description 8
- 239000007788 liquid Substances 0.000 description 7
- 238000009395 breeding Methods 0.000 description 4
- 230000001488 breeding effect Effects 0.000 description 4
- 230000001276 controlling effect Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 244000144972 livestock Species 0.000 description 3
- 244000144977 poultry Species 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 210000003608 fece Anatomy 0.000 description 2
- 230000004720 fertilization Effects 0.000 description 2
- 239000010871 livestock manure Substances 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 1
- 150000001413 amino acids Chemical class 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 239000000122 growth hormone Substances 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 239000003895 organic fertilizer Substances 0.000 description 1
- 239000010815 organic waste Substances 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 230000008635 plant growth Effects 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 239000011591 potassium Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000002881 soil fertilizer Substances 0.000 description 1
- 235000013343 vitamin Nutrition 0.000 description 1
- 239000011782 vitamin Substances 0.000 description 1
- 229940088594 vitamin Drugs 0.000 description 1
- 229930003231 vitamin Natural products 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
Images
Classifications
-
- 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
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01C—PLANTING; SOWING; FERTILISING
- A01C23/00—Distributing devices specially adapted for liquid manure or other fertilising liquid, including ammonia, e.g. transport tanks or sprinkling wagons
Abstract
The invention relates to an intelligent biogas slurry application method based on machine learning, which comprises the following steps: deploying a decision factor acquisition unit for acquiring data related to crop growth and a biogas slurry application unit for executing a specified biogas slurry application strategy; acquiring historical data related to crop growth and irrigation data; establishing a biogas slurry application model, including a state classification model and an application measure prediction model based on machine learning; training a state classification model and an application measure prediction model respectively by taking historical data as training samples; the state classification model is used for predicting the farmland state type according to the decision factor, and the application measure prediction model is used for predicting the biogas slurry application strategy according to the decision factor and the farmland state type; the decision factors are collected in real time through a decision factor collecting unit, the current farmland state type is determined through a state classification model, the biogas slurry application strategy is determined through an application measure prediction model, and the implementation is performed through a biogas slurry application unit.
Description
Technical Field
The invention relates to an intelligent biogas slurry application method and system based on machine learning and a storage medium, and belongs to the technical field of agricultural fertilization and machine learning.
Background
The biogas slurry contains various nutrients for plant growth, rich amino acids, various growth hormones, vitamins and the like, is a quick-acting organic fertilizer, and has the advantages of enhancing the soil fertilizer effect, promoting the yield and income increase of crops, inhibiting plant diseases and the like when being returned to the field.
The agricultural industry needs to accelerate the promotion of the treatment and the resource of the livestock and poultry breeding waste; the recycling of livestock and poultry breeding waste is comprehensively promoted, a new sustainable development pattern of planting and breeding combination and farming and animal circulation is constructed, and biogas slurry and harmless livestock and poultry breeding wastewater are encouraged to be scientifically returned to the field for utilization as fertilizer. The biogas slurry returning meets the national industrial development requirements, and is beneficial to promoting the green sustainable development of agriculture.
The nutrient difference of the current biogas slurry is obvious, the nutrient content change range among different biogas projects is large, and the nutrient content of the same biogas project is influenced by various factors such as fermentation raw materials, biogas project types and operation time. At present, real-time detection is difficult to achieve in farmland utilization, application amount basis is lacked in returning field utilization, and problems of insufficient or excessive biogas slurry application amount and the like often exist, so that crop yield is influenced, acid-base balance of soil is damaged, heavy metal content in soil is increased, and even surface pollution is caused;
at present, the research and development content of biogas slurry application equipment is very little, and the research on a biogas slurry scientific application method is blank; patent No. CN108156886A discloses a biogas slurry water fertilizer supply device, belonging to the field of resource and energy utilization of agricultural organic wastes. The biogas slurry irrigation device solves the problems of high cost, difficult control and the like in the process of mixing biogas slurry and water and irrigating in the prior art. This device mainly includes: the underground liquid storage tank and the above-ground closed mixing and stirring tank are arranged; the liquid storage tank is connected with the mixing and stirring tank through a biogas slurry pump; the mixing and stirring pool is also connected with a water pump and a liquid outlet, the liquid outlet is connected with a first fertilizer outlet pipe and a second fertilizer outlet pipe through a tee joint, and each pipeline is provided with an electromagnetic valve; still be equipped with display screen, operating button, battery, treater, solar cell panel and signal receiver on the mixing stirring pond, be provided with agitator motor in the middle of the top in mixing stirring pond, agitator motor is connected with the (mixing) shaft, is connected with cross stirring rake and stirring vane on the (mixing) shaft respectively, is equipped with level sensor in the mixing stirring pond. The device has realized that liquid manure mixes and regularly quantitative irrigation, and the controllability is strong, and convenient to use can find out that traditional liquid manure irrigation method is through regularly, the intelligent irrigation mode of fixed parameter, can't carry out dynamic adjustment according to the practical application scene and realize accurate fertilization and some system equipment operations are numerous and diverse, and the peasant is difficult to accept. Therefore, the dynamic adjustment of biogas slurry application is realized by combining a multidisciplinary mature technology, the irrigation quality and efficiency of the biogas slurry are improved, and the market demand is met.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an intelligent biogas slurry application method, system and storage medium based on machine learning.
The technical scheme of the invention is as follows:
an intelligent biogas slurry application method based on machine learning comprises the following steps:
deploying a decision factor acquisition unit and a biogas slurry application unit on a target farmland, wherein the decision factor acquisition unit is used for acquiring decision factors, the decision factors comprise at least one type of data related to crop growth, and the biogas slurry application unit is used for irrigating the target farmland according to a specified biogas slurry application strategy;
acquiring historical data, and acquiring data related to crop growth and irrigation data in different unit time periods according to the historical data; establishing a biogas slurry application model, wherein the biogas slurry application model comprises a state classification model and an application measure prediction model based on machine learning; acquiring feature items and corresponding feature values from historical data or obtaining target feature items and corresponding feature values through feature item calculation as training samples, and respectively training the state classification model and the application measure prediction model; the state classification model is used for predicting the farmland state type according to the decision factor, and the application measure prediction model is used for predicting the biogas slurry application measure and the application characteristic value to be adopted according to the decision factor and the farmland state type;
acquiring a decision factor through a decision factor acquisition unit, determining a farmland state type through the state classification model, inputting the decision factor and the farmland state type into an application measure prediction model, and outputting a biogas slurry application strategy consisting of biogas slurry application measures to be adopted and application characteristic values; and controlling the biogas slurry applying unit according to the biogas slurry applying strategy to irrigate a target farmland.
Preferably, the decision factor at least comprises soil data and environmental data; the soil data comprise soil humidity, soil PH value and soil nutrient content, and the environment data comprise meteorological data and environment temperature and humidity.
Preferably, the training method of the state classification model specifically includes:
obtaining soil data and environment data in different unit time periods through historical data, and classifying farmland state types in different unit time periods according to the soil data and the environment data in the unit time periods to obtain a farmland state classification group consisting of a plurality of farmland state types;
and calculating characteristic variables through soil data and environment data in unit time period, taking the characteristic variables as input of the neural network, taking a certain farmland state type in the farmland state classification group as output, and training the neural network to obtain a trained state classification model.
Preferably, the characteristic variables comprise an absorbable moisture characteristic index calculated through soil moisture, meteorological data and environment temperature and humidity and an absorbable nutrient characteristic index calculated through soil pH value and soil nutrient content.
Preferably, the application measure prediction model includes a measure selection model and a measure assignment model, and the specific method for training the application measure prediction model includes:
constructing an application measure library, wherein the application measure library comprises all biogas slurry application measures extracted from historical irrigation data;
taking the characteristic index and the farmland state type in a unit time period as the input of a neural network, and selecting at least one biogas slurry application measure from the application measure library as the output of the neural network;
constructing a selection hit rate calculation formula, wherein the selection hit rate refers to the probability that the application measures output by the neural network are completely matched with the application measures adopted in the unit time period;
constructing a loss function by taking the selection hit rate as a reference, and iteratively updating parameters of the neural network by a gradient descent method to obtain an application measure prediction model;
the method for training the measure assignment model specifically comprises the following steps:
combining the characteristic indexes, the farmland state types, the biogas slurry application measures and the corresponding application characteristic values in a unit time period into a training sample, and putting the training sample into an experience playback library;
and taking the characteristic index of each training sample, the farmland state type and the biogas slurry application measure as the input of the neural network, estimating a predicted value corresponding to the biogas slurry application measure, constructing a loss function by taking the difference value between the corresponding predicted value and the application characteristic value as a reference, and iteratively updating the parameters of the neural network by using a gradient descent method to obtain a measure assignment model.
Preferably, the biogas slurry administration measures comprise biogas slurry administration time nodes, biogas slurry and clear water ratio adjustment, biogas slurry flow rate adjustment and biogas slurry administration duration, and the administration characteristic values are numerical values of the corresponding biogas slurry administration measures.
Preferably, the target farmland is further provided with an intelligent terminal, the biogas slurry application model is established on a cloud server, and the intelligent terminal is in communication connection with the decision factor acquisition unit, the biogas slurry application unit and the cloud server, and is used for receiving the decision factors acquired by the decision factor acquisition unit, uploading the decision factors to the cloud server, receiving a biogas slurry application strategy output by the cloud server through the biogas slurry application model and the decision factors, and controlling the biogas slurry application unit to irrigate the target farmland according to the biogas slurry application strategy.
Preferably, the decision factor acquisition unit comprises a field monitoring module and a meteorological data acquisition module, and the biogas slurry application unit comprises a water and fertilizer preparation module and a water and fertilizer delivery module.
The invention also provides an intelligent biogas slurry application system based on machine learning, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the biogas slurry application method according to any embodiment of the invention.
The invention also provides a computer-readable storage medium on which a computer program is stored, wherein the program is used for implementing the biogas slurry application method according to any one of the embodiments of the invention when being executed by a processor.
The invention has the following beneficial effects:
according to the intelligent biogas slurry application method based on machine learning, disclosed by the invention, a biogas slurry application model based on machine learning is established, a biogas slurry application strategy can be adjusted in real time according to a decision factor, and biogas slurry application is automatically carried out according to the adjusted biogas slurry application strategy, so that the biogas slurry application is intelligent.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1, an intelligent biogas slurry application method based on machine learning comprises the following steps:
deploying a decision factor acquisition unit and a biogas slurry application unit on a target farmland, wherein the decision factor acquisition unit is used for acquiring decision factors, the decision factors comprise at least one type of data related to crop growth, and the biogas slurry application unit is used for irrigating the target farmland according to a specified biogas slurry application strategy;
collecting historical data of a plurality of crops planted to harvested as samples, wherein the samples can be historical data of a target farmland and historical data of other farmlands, and for other farmlands, the historical data is basically consistent with the conditions of the target farmland at least in the geographical environment and the planted crops; acquiring data and irrigation data related to crop growth in different unit time periods according to historical data, wherein the unit time period refers to one day in the embodiment, namely acquiring the data and the irrigation data related to the crop growth of each day from the crop planting to the receiving period according to the historical data; in the historical data, data related to crop growth in different unit time periods are objective data, irrigation data are empirical data, and the data are different biogas slurry application measures and corresponding characteristic values for farmers to apply biogas slurry to farmlands according to specific conditions, wherein the biogas slurry application measures are used for adjusting the mixing proportion of biogas slurry and clear water, and the characteristic values are specific numerical values of the mixing proportion;
establishing a biogas slurry application model, wherein the biogas slurry application model comprises a state classification model and an application measure prediction model based on machine learning; acquiring feature items and corresponding feature values from historical data or obtaining target feature items and corresponding feature values through feature item calculation as training samples, and respectively training the state classification model and the application measure prediction model; the state classification model is used for predicting farmland state types according to decision factors, the farmland state types are classified by experienced farmers and can be divided into N types, such as drought farmland, sufficient farmland water, sufficient farmland nutrition and the like, labels of the farmland state types are artificially added to each training sample, and then the state classification model is trained; the application measure prediction model is used for predicting biogas slurry application measures and application characteristic values to be adopted according to the decision factors and the farmland state types;
acquiring a decision factor of a target farmland in a current time period in real time through a decision factor acquisition unit, determining a farmland state type of the current target farmland through the state classification model, inputting the decision factor in the current time period and the farmland state type of the current target farmland into an application measure prediction model, and outputting a biogas slurry application strategy consisting of biogas slurry application measures and application characteristic values to be adopted; and controlling the biogas slurry applying unit according to the biogas slurry applying strategy to irrigate a target farmland.
In another embodiment of the present invention, the collected decision factors at least include soil data and environment data, the soil data includes soil humidity, soil PH, and soil nutrient content, the soil nutrient content is specifically nitrogen, phosphorus, and potassium, and the environment data includes meteorological data and environmental temperature and humidity.
In another embodiment of the present invention, the training method of the state classification model specifically includes:
obtaining soil data and environment data in different unit time periods through historical data, classifying farmland state types in different unit time periods according to the soil data and the environment data in different unit time periods, wherein the classification is carried out manually, farmers specifically judge the farmland state types in the same day according to the soil data and the environment data of each day according to experience, and mark the farmland state types, and each farmland state type summarized manually forms a farmland state classification group { A }1,A2,A3……An}；
Calculating characteristic variables through soil data and environment data in unit time period, taking the characteristic variables as input of a neural network, and classifying certain farmland state type in a farmland state classification group
As a prediction type output, a loss function is constructed based on the output farmland state type and the actual farmland state type (i.e., label) in the unit time period:
and training the neural network, and iteratively updating parameters of the neural network by a gradient descent method to obtain a trained state classification model.
In another embodiment of the present invention, the characteristic variables include an absorbable moisture characteristic index α calculated from soil humidity, meteorological data and environmental humiture, and an absorbable nutrient characteristic index β calculated from soil PH and soil nutrient content; in the embodiment, the absorbable moisture characteristic index α is k1 a1+ k2 a2+ k3 a3, where a1, a2, a3 are soil humidity, estimated precipitation amount obtained from meteorological data, and air humidity obtained from ambient temperature and humidity, k1, k2, and k3 are coefficients, k1 and k3 are assigned by artificial experience, k2 is determined by estimated weather in meteorological data, and k2 is given different values according to different weather; in this example, the absorbable nutrient characteristic index β h1 b1+ h2 b2, where b1 and b2 are the soil PH and soil nutrient content, respectively, and h1 and h2 are coefficients, assigned by manual experience.
In another embodiment of the present invention, the application measure prediction model includes a measure selection model and a measure assignment model, and the specific method for training the application measure prediction model includes:
constructing an application measure library, wherein the application measure library comprises all biogas slurry application measures extracted from historical irrigation data;
taking the characteristic index and the farmland state type in a unit time period as the input of a neural network, and selecting at least one biogas slurry application measure from the application measure library as the output of the neural network;
constructing a calculation formula of the selection hit rate
Biogas slurry application measure set for expressing output of neural network
When the biogas slurry application measures adopted in the unit time period are completely matched, the value of the indication function is 1, otherwise, the value is 0; the selection hit rate refers to the probability that the application measures output by the neural network completely match the application measures adopted in the unit time period;
constructing a loss function by taking the selection hit rate as a reference, and iteratively updating parameters of the neural network by a gradient descent method to obtain an application measure prediction model;
the method for training the measure assignment model specifically comprises the following steps:
characteristic indexes alpha and beta in unit time period and farmland state type AiBiogas slurry application measure set
And corresponding application characteristic value Ti (t)Are combined into a training sample
Putting the experience into an experience playback library;
taking the characteristic index of each training sample, the farmland state type and the biogas slurry application measure as the input of a neural network, and estimating the corresponding predicted value of the biogas slurry application measure
Constructing a loss function based on the difference between the corresponding predicted value and the application characteristic value
And (5) iteratively updating parameters of the neural network by using a gradient descent method to obtain a measure assignment model.
In another embodiment of the present invention, the biogas slurry administration measures include biogas slurry administration time node, adjustment of biogas slurry and clear water ratio, adjustment of biogas slurry flow rate, and biogas slurry administration duration, the administration characteristic values are numerical values of the corresponding biogas slurry administration measures, and for the biogas slurry administration time node, the administration characteristics are 12 points, 17: 30, for convenient use, the time nodes are converted into rational numbers by applying characteristic values, such as 12 and 17.5; the application characteristic value for adjusting the ratio of the biogas slurry to the clear water is specifically the EC value after the biogas slurry and the clear water are mixed; the application characteristic value for adjusting the biogas slurry flow is the adjusted biogas slurry flow value; the characteristic value of the biogas slurry application time is the time interval from the start of biogas slurry application to the end of biogas slurry application, and needs to be converted into a rational number.
In another embodiment of the invention, the target farmland is further provided with an intelligent terminal, the intelligent terminal can be a PC computer, a workstation or other terminals capable of transmitting and processing information, the biogas slurry application model is established on a cloud server, and the intelligent terminal is in communication connection with the decision factor acquisition unit, the biogas slurry application unit and the cloud server, is used for receiving the decision factor acquired by the decision factor acquisition unit, uploading the decision factor to the cloud server, receiving a biogas slurry application strategy output by the cloud server through the biogas slurry application model and the decision factor, and controlling the biogas slurry application unit to irrigate the target farmland according to the biogas slurry application strategy.
In another embodiment of the present invention, the decision factor collecting unit comprises a field monitoring module and a meteorological data collecting module, and the biogas slurry applying unit comprises a water and fertilizer preparing module and a water and fertilizer conveying module. The field monitoring module comprises a plurality of sensors, at least one of a temperature and humidity sensor, a soil humidity sensor, a PH sensor and an electrochemical sensor is used for collecting soil humidity, a soil PH value, soil nutrient content and environment temperature and humidity respectively; the weather data acquisition module is used for receiving weather forecast through the Internet to obtain weather data, wherein the weather data comprises predicted weather, predicted precipitation and the like; the water and fertilizer preparation comprises a biogas slurry pool, a clean water pool, a biogas slurry electric regulating valve, a clean water electric regulating valve, a centrifugal pump and the like, and can regulate the fertilizing time and the application flow of the mixed liquid of water and biogas slurry according to the set EC value of the biogas slurry; the water and fertilizer conveying module comprises an electromagnetic valve and a field pipeline and is used for conveying biogas slurry to each part of the field.
The invention also provides an intelligent biogas slurry application system based on machine learning, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the biogas slurry application method according to any embodiment of the invention.
The invention also provides a computer-readable storage medium on which a computer program is stored, wherein the program is used for implementing the biogas slurry application method according to any one of the embodiments of the invention when being executed by a processor.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. The intelligent biogas slurry application method based on machine learning is characterized by comprising the following steps:
deploying a decision factor acquisition unit and a biogas slurry application unit on a target farmland, wherein the decision factor acquisition unit is used for acquiring decision factors, the decision factors comprise at least one type of data related to crop growth, and the biogas slurry application unit is used for irrigating the target farmland according to a specified biogas slurry application strategy;
acquiring historical data, and acquiring data related to crop growth and irrigation data in different unit time periods according to the historical data; establishing a biogas slurry application model, wherein the biogas slurry application model comprises a state classification model and an application measure prediction model based on machine learning; acquiring feature items and corresponding feature values from historical data or obtaining target feature items and corresponding feature values through feature item calculation as training samples, and respectively training the state classification model and the application measure prediction model; the state classification model is used for predicting the farmland state type according to the decision factor, and the application measure prediction model is used for predicting the biogas slurry application measure and the application characteristic value to be adopted according to the decision factor and the farmland state type;
acquiring a decision factor through a decision factor acquisition unit, determining a farmland state type through the state classification model, inputting the decision factor and the farmland state type into an application measure prediction model, and outputting a biogas slurry application strategy consisting of biogas slurry application measures to be adopted and application characteristic values; and controlling the biogas slurry applying unit according to the biogas slurry applying strategy to irrigate a target farmland.
2. The machine learning-based intelligent biogas slurry application method according to claim 1, characterized in that: the decision factor at least comprises soil data and environmental data; the soil data comprise soil humidity, soil PH value and soil nutrient content, and the environment data comprise meteorological data and environment temperature and humidity.
3. The machine learning-based intelligent biogas slurry application method according to claim 2, wherein the training method of the state classification model specifically comprises the following steps:
obtaining soil data and environment data in different unit time periods through historical data, and classifying farmland state types in different unit time periods according to the soil data and the environment data in the unit time periods to obtain a farmland state classification group consisting of a plurality of farmland state types;
and calculating characteristic variables through soil data and environment data in unit time period, taking the characteristic variables as input of the neural network, taking a certain farmland state type in the farmland state classification group as output, and training the neural network to obtain a trained state classification model.
4. The machine learning-based intelligent biogas slurry application method according to claim 3, characterized in that: the characteristic variables comprise an absorbable moisture characteristic index obtained by calculating soil moisture, meteorological data and environment temperature and humidity and an absorbable nutrient characteristic index obtained by calculating the soil pH value and the soil nutrient content.
5. The machine learning-based intelligent biogas slurry application method according to claim 3, wherein the application measure prediction model comprises a measure selection model and a measure assignment model, and the specific method for training the application measure prediction model comprises the following steps:
constructing an application measure library, wherein the application measure library comprises all biogas slurry application measures extracted from historical irrigation data;
taking the characteristic index and the farmland state type in a unit time period as the input of a neural network, and selecting at least one biogas slurry application measure from the application measure library as the output of the neural network;
constructing a selection hit rate calculation formula, wherein the selection hit rate refers to the probability that the application measures output by the neural network are completely matched with the application measures adopted in the unit time period;
constructing a loss function by taking the selection hit rate as a reference, and iteratively updating parameters of the neural network by a gradient descent method to obtain an application measure prediction model;
the method for training the measure assignment model specifically comprises the following steps:
combining the characteristic indexes, the farmland state types, the biogas slurry application measures and the corresponding application characteristic values in a unit time period into a training sample, and putting the training sample into an experience playback library;
and taking the characteristic index of each training sample, the farmland state type and the biogas slurry application measure as the input of the neural network, estimating a predicted value corresponding to the biogas slurry application measure, constructing a loss function by taking the difference value between the corresponding predicted value and the application characteristic value as a reference, and iteratively updating the parameters of the neural network by using a gradient descent method to obtain a measure assignment model.
6. The machine learning-based intelligent biogas slurry application method according to claim 5, characterized in that: the biogas slurry application measures comprise biogas slurry application time nodes, adjustment of biogas slurry and clear water proportion, adjustment of biogas slurry flow and biogas slurry application duration, and the application characteristic values are numerical values of the corresponding biogas slurry application measures.
7. The machine learning-based intelligent biogas slurry application method according to claim 1, characterized in that: the target farmland is also provided with an intelligent terminal, the biogas slurry application model is established on a cloud server, and the intelligent terminal is in communication connection with the decision factor acquisition unit, the biogas slurry application unit and the cloud server, is used for receiving the decision factors acquired by the decision factor acquisition unit, uploading the decision factors to the cloud server, receiving a biogas slurry application strategy output by the cloud server through the biogas slurry application model and the decision factors, and controlling the biogas slurry application unit to irrigate the target farmland according to the biogas slurry application strategy.
8. The machine learning-based intelligent biogas slurry application method according to claim 7, characterized in that: the decision factor acquisition unit comprises a field monitoring module and a meteorological data acquisition module, and the biogas slurry application unit comprises a water and fertilizer preparation module and a water and fertilizer conveying module.
9. An intelligent biogas slurry application system based on machine learning, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the biogas slurry application method according to any one of claims 1 to 8.
10. A computer-readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements the biogas slurry administration method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110986629.8A CN113642729A (en) | 2021-08-26 | 2021-08-26 | Intelligent biogas slurry application method and system based on machine learning and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110986629.8A CN113642729A (en) | 2021-08-26 | 2021-08-26 | Intelligent biogas slurry application method and system based on machine learning and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113642729A true CN113642729A (en) | 2021-11-12 |
Family
ID=78423972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110986629.8A Pending CN113642729A (en) | 2021-08-26 | 2021-08-26 | Intelligent biogas slurry application method and system based on machine learning and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642729A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114935590A (en) * | 2022-05-30 | 2022-08-23 | 江苏大学 | Biogas slurry water quality online monitoring device, and biogas slurry accurate fertilizer preparation and returning system and method |
| CN116451886A (en) * | 2023-06-20 | 2023-07-18 | 创辉达设计股份有限公司 | High-standard farmland water balance calculation method |
| CN117688404A (en) * | 2024-02-02 | 2024-03-12 | 北京市农林科学院智能装备技术研究中心 | Intelligent fertilization formula decision method, intelligent fertilization formula decision device, intelligent fertilization formula decision equipment, intelligent fertilization formula decision medium and program product |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105825230A (en) * | 2016-03-15 | 2016-08-03 | 中国农业大学 | Soil moisture status prediction method and system based on DBN (Deep Belief Network) model |
| CN106707767A (en) * | 2017-03-13 | 2017-05-24 | 山东农业大学 | System and method for integrally and intelligently controlling water and fertilizer in field based on multi-source information fusion |
| CN107451522A (en) * | 2017-04-28 | 2017-12-08 | 山东省农业可持续发展研究所 | A kind of agricultural arid monitoring and early alarming and forecasting method |
| CN107945042A (en) * | 2017-11-29 | 2018-04-20 | 上海华维节水灌溉股份有限公司 | A kind of plant growth irrigation decision control system |
| CN109258044A (en) * | 2018-08-30 | 2019-01-25 | 北京农业智能装备技术研究中心 | A kind of field water fertilizer managing and control system and method based on biogas slurry |
| CN110122024A (en) * | 2019-06-10 | 2019-08-16 | 福建省致青生态环保有限公司 | A kind of intelligent integral fertilization system for applying biogas slurry |
| CN111126662A (en) * | 2019-11-25 | 2020-05-08 | 中工武大设计研究有限公司 | Irrigation decision making method, device, server and medium based on big data |
| CN111369093A (en) * | 2018-12-26 | 2020-07-03 | 天云融创数据科技（北京）有限公司 | Irrigation method and device based on machine learning |
| CN112020972A (en) * | 2020-08-26 | 2020-12-04 | 江苏农林职业技术学院 | Intelligent water and fertilizer integrated system for hole tray type organic rice hard ground seedling raising |
| CN112050856A (en) * | 2020-09-08 | 2020-12-08 | 安徽大学 | Industry ecological garden mode for intelligently monitoring blue-green algae resource utilization |
| CN112668705A (en) * | 2021-03-17 | 2021-04-16 | 清华大学 | Drought index monitoring method and system based on deep learning |
| CN213603209U (en) * | 2020-10-16 | 2021-07-06 | 山东沐雨天禾智慧农业有限公司 | Biogas slurry intelligent irrigation system based on big data crop model |
-
2021
- 2021-08-26 CN CN202110986629.8A patent/CN113642729A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105825230A (en) * | 2016-03-15 | 2016-08-03 | 中国农业大学 | Soil moisture status prediction method and system based on DBN (Deep Belief Network) model |
| CN106707767A (en) * | 2017-03-13 | 2017-05-24 | 山东农业大学 | System and method for integrally and intelligently controlling water and fertilizer in field based on multi-source information fusion |
| CN107451522A (en) * | 2017-04-28 | 2017-12-08 | 山东省农业可持续发展研究所 | A kind of agricultural arid monitoring and early alarming and forecasting method |
| CN107945042A (en) * | 2017-11-29 | 2018-04-20 | 上海华维节水灌溉股份有限公司 | A kind of plant growth irrigation decision control system |
| CN109258044A (en) * | 2018-08-30 | 2019-01-25 | 北京农业智能装备技术研究中心 | A kind of field water fertilizer managing and control system and method based on biogas slurry |
| CN111369093A (en) * | 2018-12-26 | 2020-07-03 | 天云融创数据科技（北京）有限公司 | Irrigation method and device based on machine learning |
| CN110122024A (en) * | 2019-06-10 | 2019-08-16 | 福建省致青生态环保有限公司 | A kind of intelligent integral fertilization system for applying biogas slurry |
| CN111126662A (en) * | 2019-11-25 | 2020-05-08 | 中工武大设计研究有限公司 | Irrigation decision making method, device, server and medium based on big data |
| CN112020972A (en) * | 2020-08-26 | 2020-12-04 | 江苏农林职业技术学院 | Intelligent water and fertilizer integrated system for hole tray type organic rice hard ground seedling raising |
| CN112050856A (en) * | 2020-09-08 | 2020-12-08 | 安徽大学 | Industry ecological garden mode for intelligently monitoring blue-green algae resource utilization |
| CN213603209U (en) * | 2020-10-16 | 2021-07-06 | 山东沐雨天禾智慧农业有限公司 | Biogas slurry intelligent irrigation system based on big data crop model |
| CN112668705A (en) * | 2021-03-17 | 2021-04-16 | 清华大学 | Drought index monitoring method and system based on deep learning |
Non-Patent Citations (3)
| Title |
|---|
| XIUMEI JIA等: "Design of Field Integrative Irrigation Control System Based on Fuzzy Control and PLC", 《EMERGING RESEARCH IN ARTIFICIAL INTELLIGENCE AND COMPUTIONAL INTELLIGENCE》, vol. 237, 24 September 2011 (2011-09-24), pages 1 - 2 * |
| 李睿: "基于GIS与WSN技术的沼液自动灌溉系统", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 2013, 15 December 2013 (2013-12-15), pages 138 - 394 * |
| 王鑫瑶: "不同沼液施用量对橡胶苗生长和橡胶林土壤肥力质量的影响", 《中国优秀硕士学位论文全文数据库 基础科学辑》, no. 2020, 15 August 2020 (2020-08-15), pages 008 - 24 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114935590A (en) * | 2022-05-30 | 2022-08-23 | 江苏大学 | Biogas slurry water quality online monitoring device, and biogas slurry accurate fertilizer preparation and returning system and method |
| CN116451886A (en) * | 2023-06-20 | 2023-07-18 | 创辉达设计股份有限公司 | High-standard farmland water balance calculation method |
| CN116451886B (en) * | 2023-06-20 | 2023-10-10 | 创辉达设计股份有限公司 | High-standard farmland water balance calculation method |
| CN117688404A (en) * | 2024-02-02 | 2024-03-12 | 北京市农林科学院智能装备技术研究中心 | Intelligent fertilization formula decision method, intelligent fertilization formula decision device, intelligent fertilization formula decision equipment, intelligent fertilization formula decision medium and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111557159B (en) | Water and fertilizer integrated machine control system with crop nutrient demand analysis function and control method thereof | |
| CN113642729A (en) | Intelligent biogas slurry application method and system based on machine learning and storage medium | |
| CN111061322A (en) | Water and fertilizer integrated system based on artificial intelligence | |
| CN109874477B (en) | Agricultural park fertilizer applicator hosting method and system | |
| CN103838144B (en) | Caulis Sacchari sinensis precision farming drip irrigation based on Internet of Things soil analysis modeling control method | |
| CN205883318U (en) | Agricultural thing networking remote monitoring and control system | |
| CN105494033B (en) | A kind of intelligent water-saving irrigation method based on crop demand | |
| CN109601347A (en) | A kind of agricultural automation irrigation system | |
| CN112042353A (en) | Water and fertilizer accurate decision method and system suitable for sunlight greenhouse | |
| CN112540563A (en) | Intelligent agricultural control system and control method based on Internet of things | |
| CN106171228A (en) | A kind of the Integration of Water into Fertilizer scheme based on Internet of Things | |
| CN204616643U (en) | A kind of novel Internet of Things without native organic vegetable nutrient solution cyclic utilization system | |
| CN207780640U (en) | A kind of water-fertilizer integrated intelligent system | |
| CN114258774A (en) | A liquid manure integration fertilization system for farming | |
| CN211149296U (en) | Water and fertilizer integrated system based on artificial intelligence | |
| CN108985664A (en) | A kind of intelligence farm field monitoring management system and method | |
| CN213848015U (en) | Crop water-saving irrigation measurement and control system based on multi-source information fusion | |
| Pandey et al. | A Low Cost Smart Irrigation Planning Based on Machine Learning and Internet of Things | |
| CN1640855A (en) | Granule farmyard manure and its preparing method | |
| CN210247520U (en) | Regional intelligent irrigation system of tomato liquid manure | |
| CN208768585U (en) | Biogas residue and biogas liquid Intelligent irrigation system | |
| Shabbir et al. | A review of iot based automated irrigation system using solar power | |
| Meduri et al. | A sophisticated irrigation system with passive and analogue sensors over web using orange Pi | |
| CN109526342A (en) | A kind of accurate liquid manure one irrigation system remotely controlled based on ZigBee | |
| CN214757871U (en) | Novel fertigation and vegetation monitoring all-in-one |
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 |