CN115545962A - Crop growth period control method and system based on multi-sensor system - Google Patents
Crop growth period control method and system based on multi-sensor system Download PDFInfo
- Publication number
- CN115545962A CN115545962A CN202211078778.5A CN202211078778A CN115545962A CN 115545962 A CN115545962 A CN 115545962A CN 202211078778 A CN202211078778 A CN 202211078778A CN 115545962 A CN115545962 A CN 115545962A
- Authority
- CN
- China
- Prior art keywords
- data
- crop growth
- information
- crop
- sensor system
- 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 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000003062 neural network model Methods 0.000 claims abstract description 14
- 238000005457 optimization Methods 0.000 claims abstract description 7
- 239000002245 particle Substances 0.000 claims abstract description 7
- 230000002349 favourable effect Effects 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 15
- 239000002689 soil Substances 0.000 claims description 10
- 238000002790 cross-validation Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 239000002253 acid Substances 0.000 claims description 3
- 239000003513 alkali Substances 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 description 9
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 238000012897 Levenberg–Marquardt algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Marine Sciences & Fisheries (AREA)
- General Business, Economics & Management (AREA)
- Mining & Mineral Resources (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of information, and discloses a crop growth cycle management and control method and system based on a multi-sensor system. The method comprises the steps of obtaining crop parameters through a crop growth period control system or a robot dynamic patrol and an unmanned aerial vehicle aerial photograph, setting a learning group and a special environment learning group, initializing a BP neural network model by using a particle swarm optimization (m-PSO) algorithm to obtain a trained prediction model, inputting the prediction model into the special environment learning group, outputting predicted information, inputting the information into an established model to simulate actual conditions, and generating the most favorable decision.
Description
Technical Field
The invention relates to the technical field of information, in particular to a crop growth cycle control method and system based on a multi-sensor system.
Background
Currently existing crop monitoring algorithms include crop information prediction methods based on weighted PCA, m-PSO algorithms and ANN hybrid models. Preprocessing data, predicting a loss value in the acquired agricultural data by using an alternating least square Algorithm (ALS) in Principal Component Analysis (PCA) according to the acquired agricultural data to obtain complete data, normalizing the complete data, extracting features of the preprocessed data by using weighted principal component analysis (w-PCA) to obtain new extracted features, and dividing the new features into a training set and a test set. Inputting the training set into an artificial neural network ANN model, initializing initial bias b and initial weight omega in the artificial neural network ANN model by using a Particle Swarm Optimization (PSO) algorithm to obtain a trained prediction model, inputting a test set, using the cross validation trained model, and then outputting prediction information. In the neural artificial neural network ANN model, a Levenberg-Marquardt algorithm is used as a back propagation training algorithm.
And the deep mining and intelligent decision algorithm of agricultural big data also carries out data sharing, data retrieval, data analysis and data display according to the existing big data storage information. Selecting related data or samples from original data, checking the integrity and consistency of the data, eliminating noise data, determining the type of knowledge to be found, selecting a proper data mining algorithm according to a determined target, extracting the related knowledge and expressing the related knowledge in a certain mode, evaluating the mode found in the data mining process, and making a decision.
Such as: the crop disease detection algorithm based on deep learning is a relatively excellent and mature algorithm, the method comprises the steps of firstly obtaining images of a training set and a testing set, carrying out online data enhancement on the images through machine graying, left-right turning, up-down turning, diagonal turning and the like, and carrying out comparison calculation on an obtained prediction result and a real label to obtain Loss through migration learning with different learning rates and an adaptive multi-scale resnet50 network with Focal Loss as a Loss function on the images of the training set after preprocessing. The model parameters are updated by a gradient descent algorithm with momentum. And finally, detecting crop diseases on the trained model by using the test set.
In the prior art, a crop information prediction method based on weighted PCA, an m-PSO algorithm and an ANN mixed model and a deep mining and intelligent decision algorithm of agricultural big data are all used for extracting information from the existing agricultural data. However, different regions have different operating environments, the same crop has completely different cultivation requirements in different regions, the same crop is inevitably trapped in a single repeated swamp pool only by means of calculation and analysis based on the existing data, and the prediction accuracy is greatly limited. Although the data according to which the algorithm predicts is the image of the actual crop, the crop disease analysis is very difficult to be very accurate only by relying on the single data of the image, and the accuracy of the decision is yet to be perfected.
We observe that the audience of the current widely used general algorithm model is a plurality of ubiquitous crops, and the good prediction control effect of the common algorithm model is difficult to accurately and properly exert on a plurality of special crops. Most of the current algorithms are based on single influence factors, for example, crop information prediction methods based on weighted PCA, m-PSO algorithms and ANN mixed models and deep mining and intelligent decision algorithms of agricultural big data are all obtained from existing agricultural data and trained by models to obtain prediction results. The crop disease detection algorithm based on deep learning is only analyzed from the image of the crop, and the analyzed data is single. The comprehensiveness and accuracy of the prediction result are difficult to ensure, and the implementation of the output scheme is often difficult to achieve the expected effect.
Meanwhile, under the actual condition, the condition of each aspect is difficult to achieve the optimum condition, and the judgment of the minimum loss is often calculated by combining multiple considerations, so that the loss can be reduced to the maximum degree even in sudden severe environment.
Disclosure of Invention
Technical problem to be solved
In order to overcome the defects in the prior art, the invention provides a crop growth cycle control method and system based on a multi-sensor system, so as to solve the problems.
(II) technical scheme
In order to achieve the above purpose, the invention provides the following technical scheme:
the utility model provides a crop growth cycle management and control system based on multisensor system, includes that central control module and data acquisition module constitute, and central control module mainly comprises singlechip and relay, and data acquisition module mainly comprises temperature sensor, light intensity sensor, soil PH sensor, air humidity sensor and image acquisition device, and wherein the singlechip links to each other with the relay, and data acquisition module links to each other with the singlechip, and the relay meets with the power.
A crop growth cycle management and control method based on a multi-sensor system comprises the following steps:
the first step is as follows: acquiring crop parameters through a crop growth period control system based on a multi-sensor system or a robot dynamic patrol and an unmanned aerial vehicle aerial photograph, and setting a learning group and a special environment learning group;
the second step is that: predicting loss values in the acquired data by using a least square method (ALS) for the learning group to obtain complete data, and normalizing the complete data;
the third step: inputting the processed data into a BP neural network model, and initializing an initial bias b and an initial weight omega in the BP neural network model by using a particle swarm optimization (m-PSO) algorithm to obtain a trained prediction model;
the fourth step: inputting the special environment learning group, outputting the predicted information, and comparing the predicted information with the actual information;
the fifth step: and inputting the information acquired by the data acquisition module controlled by the single chip microcomputer into the established model to simulate the actual condition, and finally generating the most favorable decision.
Preferably, in the first step, the step of acquiring the crop parameters by the crop growth cycle management and control system based on the multi-sensor system is as follows: the single chip microcomputer controls the data acquisition module to acquire the parameters of the crop growth at regular time.
Preferably, the parameters of the learning group in the first step are air humidity, temperature, illumination intensity, soil PH and images of crop growth required by growth under appropriate conditions;
the parameters of the special environment learning group are information of water shortage environment, low temperature and high temperature environment and different acid and alkali soil environments.
Preferably, the crops in the fifth step are more common crops, and the decision can be made by combining the existing data of the large database and the real-time data collected on site.
Preferably, the decision obtaining content in the sixth step is as follows: the information acquired by the data acquisition module controlled by the single chip microcomputer is input into the trained BP neural network model in real time, the loss is continuously reduced through gradient descent, and cross validation training is carried out on the information and the results of multiple previous experiments to obtain the current optimal decision.
(III) advantageous effects
Compared with the prior art, the crop growth cycle management and control method and system based on the multi-sensor system have the following beneficial effects:
1. compared with the prior art, the crop growth cycle control method and system based on the multi-sensor system improve software and hardware cooperation strategies and improve the application range and expansibility of the algorithm.
2. The crop growth cycle control method and the crop growth cycle control system based on the multi-sensor system can be used for deeply training and learning the model based on a large amount of actual data, can realize universality of most conventional crops and specificity of part special crops, can be used for learning and training detection data of growth conditions and disease conditions of crops by using the sensors, can finally output operation decisions in two aspects of nutrition and disease removal, and ensure sufficient yield and sufficient yield of agricultural products in two dimensions.
3. According to the crop growth cycle control method and system based on the multi-sensor system, in the aspect of algorithm training, due to the fact that a deep neural network and a gradual learning training method are combined, compared with a general machine learning algorithm, the system is more comprehensive and complete.
4. According to the crop growth period control method and system based on the multi-sensor system, in the aspect of decision generation, due to the fact that natural environment changes are measured, no method is available for enabling all natural environments to be suitable for crop growth, and the algorithm can match data collected by the current environment with original special environment data in the algorithm before decision making, so that the algorithm which ensures safe growth of crops and is minimum in loss is obtained. Meanwhile, the historical experience data is formed according to each decision generation, and the data can carry out secondary training on the model, so that the system is closed and self-upgraded, and the confidence coefficient of the next decision is improved. Compared with the traditional algorithm, the upgrading mechanism can enable the algorithm to have stronger flexibility, greatly reduce the dependence on data and enable the system operation cost to be controllable.
Drawings
FIG. 1 is a block diagram of a hardware system according to an embodiment of the present invention;
FIG. 2 is a schematic control flow chart according to an embodiment of the present invention;
FIG. 3 is a block diagram of a task decision flow framework according to an embodiment of the present invention;
FIG. 4 is a block diagram of a task decision process according to 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.
Examples
Referring to fig. 1, the crop growth cycle management and control system based on a multi-sensor system according to an embodiment of the present invention includes a central control module and a data acquisition module, the central control module mainly includes a single chip microcomputer and a relay, the data acquisition module mainly includes a temperature sensor, a light intensity sensor, a soil PH sensor, an air humidity sensor and an image acquisition device, wherein the single chip microcomputer is connected to the relay, the data acquisition module is connected to the single chip microcomputer, the relay is connected to a power supply, and the central control module controls each sensor to collect environmental data at regular time through the single chip microcomputer and returns the environmental data to a terminal of the central control module for further learning analysis and decision generation.
Referring to fig. 2 to 4, the method for controlling the growth cycle of a crop based on a multi-sensor system according to an embodiment of the present invention includes the following steps:
1) Data acquisition and arrangement of special crops: the flow can be divided into two modules for processing. Module 1 is through single chip microcomputer control air humidity sensor, temperature sensor, light intensity sensor, soil PH sensor and image acquisition device, regularly gathers special crop and grows required air humidity, temperature, illumination intensity, soil PH under the suitable condition to and the image that the crop grows. The data are collected and set into a learning group through a single chip microcomputer. And the module 2 is a special environment learning group. The system is respectively provided with environment information storage spaces such as a water shortage environment, a low-temperature and high-temperature environment, different acid and alkali soil and the like, the information under various environments is collected at regular time through the single chip microcomputer control data collection module, and the information is collected.
2) Establishing and learning an algorithm model: and (3) analyzing the learning group data by using a least square method (ALS) in Principal Component Analysis (PCA), predicting a loss value in the acquired data to obtain complete data, and performing normalization processing on the complete data. And inputting the processed data into a BP neural network model, and initializing an initial bias b and an initial weight omega in the human BP neural network model by using a particle swarm optimization (m-PSO) algorithm to obtain a trained prediction model. Then inputting the special environment learning group, and then outputting the predicted information to be compared with the actual information. The Levenberg-Marquardt algorithm is used as the back-propagation training algorithm.
3) And (3) intelligent decision generation: the information acquired by the multiple sensors is controlled by the single chip microcomputer and is input into the trained BP neural network model in real time, loss is continuously reduced through gradient reduction, and cross validation training is carried out on the information and results of multiple previous experiments to obtain the current optimal decision. So as to improve the yield of the crops to the maximum extent. Meanwhile, each decision is conveyed back to the second section again for training again, and the original model is continuously trained and self-perfected by relying on a deep learning network framework and an established model to form a good closed-loop model.
The following are examples of methods:
(1) Collecting and processing under a suitable environment: each sensor is controlled by the single chip microcomputer to collect data at regular time, the data are collected and integrated, and special data collection is carried out in the environments of water shortage, light shortage, low temperature, high temperature and the like.
(2) Establishing and learning an algorithm model: and (3) using a least square method ALS in PCA to predict loss values in the collected data by using the learning group data collected by the single chip microcomputer to obtain complete data, and performing normalization processing on the complete data. Inputting the processed data into a BP neural network model, and initializing an initial bias b and an initial weight omega in the BP neural network model by using a particle swarm optimization (m-PSO) algorithm to obtain a trained prediction model. Then inputting the special environment learning group, and then outputting the predicted information to be compared with the actual information.
(3) And (3) intelligent decision generation: and inputting the data acquired by the multiple sensors in real time into the established model to simulate the actual situation, finally generating the most favorable decision at the moment, and returning the simulation to the model to learn again. The algorithm is continuously improved, so that the decision is more accurate, the crops can be accurately controlled to the maximum degree, and the yield is improved.
According to the method and the system for controlling the crop growth cycle based on the multi-sensor system, provided by the embodiment of the invention, the crop growth cycle based on the multi-sensor system is controlled by a robot dynamic patrol and an unmanned aerial vehicle aerial photography to obtain crop parameters, and a learning group and a special environment learning group are set; predicting loss values in the acquired data by using a least square method (ALS) for the learning group to obtain complete data, and normalizing the complete data; inputting the processed data into a BP neural network model, and initializing an initial bias b and an initial weight omega in the BP neural network model by using a particle swarm optimization (m-PSO) algorithm to obtain a trained prediction model; inputting a special environment learning group, outputting predicted information, and comparing the predicted information with actual information; and the information acquired by the data acquisition module controlled by the single chip microcomputer is input into the established model to simulate the actual condition, so that the most favorable decision is generated.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. The utility model provides a crop growth cycle management and control system based on multisensor system, its characterized in that, includes central control module and data acquisition module and constitutes, and central control module mainly comprises singlechip and relay, and data acquisition module mainly comprises temperature sensor, light intensity sensor, soil PH sensor, air humidity sensor and image acquisition device, and the singlechip links to each other with the relay, and data acquisition module links to each other with the singlechip, and the relay meets with the power.
2. A crop growth cycle management and control method based on a multi-sensor system is characterized by comprising the following steps:
the first step is as follows: acquiring crop parameters through a crop growth cycle management and control system based on a multi-sensor system or dynamic patrol of a robot and aerial photography of an unmanned aerial vehicle, and setting a learning group and a special environment learning group;
the second step is that: predicting loss values in the acquired data by using a least square method (ALS) for the learning group to obtain complete data, and normalizing the complete data;
the third step: inputting the processed data into a BP neural network model, and initializing an initial bias b and an initial weight omega in the BP neural network model by using a particle swarm optimization (m-PSO) algorithm to obtain a trained prediction model;
the fourth step: inputting the special environment learning group, outputting the predicted information, and comparing the predicted information with the actual information;
the fifth step: and inputting the information acquired by the data acquisition module controlled by the single chip microcomputer into the established model to simulate the actual condition, and finally generating the most favorable decision.
3. The multi-sensor system based crop growth cycle management and control method according to claim 2, characterized in that: in the first step, the step of acquiring the crop parameters by the crop growth cycle management and control system based on the multi-sensor system is as follows: the single chip microcomputer controls the data acquisition module to acquire the parameters of crop growth at regular time.
4. The method for managing and controlling the growth cycle of crops based on a multi-sensor system according to claim 2, wherein: the parameters of the learning group in the first step are air humidity, temperature, illumination intensity, soil PH and crop growth images required by growth under appropriate conditions;
the parameters of the special environment learning group are information of water shortage environment, low temperature and high temperature environment and different acid and alkali soil environments.
5. The multi-sensor system based crop growth cycle management and control method according to claim 2, characterized in that: and if the crops in the fifth step are more common crops, the decision can be made by combining the existing data of the large database and the real-time data acquired on site.
6. The method for managing and controlling the growth cycle of crops based on a multi-sensor system according to claim 2, wherein: the decision acquisition content in the sixth step is as follows: the information acquired by the data acquisition module controlled by the single chip microcomputer is input into the trained BP neural network model in real time, the loss is continuously reduced through gradient descent, and cross validation training is carried out on the information and the results of multiple previous experiments to obtain the current optimal decision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211078778.5A CN115545962A (en) | 2022-09-05 | 2022-09-05 | Crop growth period control method and system based on multi-sensor system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211078778.5A CN115545962A (en) | 2022-09-05 | 2022-09-05 | Crop growth period control method and system based on multi-sensor system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115545962A true CN115545962A (en) | 2022-12-30 |
Family
ID=84725017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211078778.5A Pending CN115545962A (en) | 2022-09-05 | 2022-09-05 | Crop growth period control method and system based on multi-sensor system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115545962A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117218523A (en) * | 2023-07-26 | 2023-12-12 | 四川省农业机械科学研究院 | Asparagus harvesting system based on machine vision |
-
2022
- 2022-09-05 CN CN202211078778.5A patent/CN115545962A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117218523A (en) * | 2023-07-26 | 2023-12-12 | 四川省农业机械科学研究院 | Asparagus harvesting system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110598736B (en) | Power equipment infrared image fault positioning, identifying and predicting method | |
| CN107289998B (en) | CAN bus based pig house environment temperature intelligent monitoring system | |
| CN107085732B (en) | Cowshed environment ammonia intelligent monitoring system based on wireless sensor network | |
| CN102183621B (en) | Aquaculture dissolved oxygen concentration online forecasting method and system | |
| CN110333692B (en) | Pig heating automatic monitoring and diagnosis system based on thermal infrared | |
| CN108921359A (en) | A kind of distribution gas density prediction technique and device | |
| CN107290481B (en) | Cowshed environment ammonia intelligent detection system based on wireless sensor network | |
| CN114169638A (en) | Water quality prediction method and device | |
| CN114297907A (en) | Greenhouse environment spatial distribution prediction method and device | |
| CN110991776A (en) | Method and system for realizing water level prediction based on GRU network | |
| CN115545962A (en) | Crop growth period control method and system based on multi-sensor system | |
| CN109165770A (en) | Novel photovoltaic power forecasting method based on AFSA-Elman | |
| CN114627467A (en) | Rice growth period identification method and system based on improved neural network | |
| CN114169374A (en) | Cable-stayed bridge stay cable damage identification method and electronic equipment | |
| CN115812634A (en) | Pre-incubation hatching egg fertilization information nondestructive sorting method and device | |
| CN114418183B (en) | Livestock and poultry health sign big data internet of things detection system | |
| CN117391482B (en) | Greenhouse temperature intelligent early warning method and system based on big data monitoring | |
| CN116661530A (en) | Intelligent control system and method in edible fungus industrial cultivation | |
| CN114898405A (en) | Portable broiler chicken abnormity monitoring system based on edge calculation | |
| CN116128879B (en) | Lightweight transmission line defect detection method and device | |
| CN117406593A (en) | Intelligent data processing method and system applied to fishery management | |
| CN115861235A (en) | Flotation tailing ash content prediction method based on multi-feature data fusion | |
| CN113468823B (en) | Optical module damage detection method and system based on machine learning | |
| CN115841446A (en) | Rapid detection system and method for fault risk of solar heat collection field | |
| CN118152899B (en) | Environment perception monitoring method and system |
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 |