CN116647586A - Method for realizing remote control of water and fertilizer integrated intelligent pump house by cloud computing - Google Patents
Method for realizing remote control of water and fertilizer integrated intelligent pump house by cloud computing Download PDFInfo
- Publication number
- CN116647586A CN116647586A CN202310903920.3A CN202310903920A CN116647586A CN 116647586 A CN116647586 A CN 116647586A CN 202310903920 A CN202310903920 A CN 202310903920A CN 116647586 A CN116647586 A CN 116647586A
- Authority
- CN
- China
- Prior art keywords
- unit
- water
- data
- fertilizer integrated
- integrated intelligent
- 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
- 239000003337 fertilizer Substances 0.000 title claims abstract description 63
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 80
- 238000012545 processing Methods 0.000 claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 230000005540 biological transmission Effects 0.000 claims abstract description 17
- 230000005856 abnormality Effects 0.000 claims abstract description 7
- 230000001105 regulatory effect Effects 0.000 claims abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims description 38
- 238000004458 analytical method Methods 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 25
- 238000007726 management method Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 16
- 238000013480 data collection Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 10
- 125000003275 alpha amino acid group Chemical group 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 9
- 150000001875 compounds Chemical class 0.000 claims description 9
- 230000001276 controlling effect Effects 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 7
- 235000008694 Humulus lupulus Nutrition 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 6
- 230000015654 memory Effects 0.000 claims description 6
- 238000000926 separation method Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 abstract description 9
- 238000004891 communication Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 230000003044 adaptive effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 241000282461 Canis lupus Species 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 210000003608 fece Anatomy 0.000 description 2
- 230000004720 fertilization Effects 0.000 description 2
- 238000003973 irrigation Methods 0.000 description 2
- 230000002262 irrigation Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 239000010871 livestock manure Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 101150064138 MAP1 gene Proteins 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2132—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on discrimination criteria, e.g. discriminant analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/54—Interprogram communication
- G06F9/546—Message passing systems or structures, e.g. queues
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06N3/048—Activation functions
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/05—Agriculture
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/20—Information sensed or collected by the things relating to the thing itself
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/30—Information sensed or collected by the things relating to resources, e.g. consumed power
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y30/00—IoT infrastructure
- G16Y30/10—Security thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/30—Control
- G16Y40/35—Management of things, i.e. controlling in accordance with a policy or in order to achieve specified objectives
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/40—Maintenance of things
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/50—Safety; Security of things, users, data or systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0002—Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission rate
- H04L1/0003—Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission rate by switching between different modulation schemes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1029—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers using data related to the state of servers by a load balancer
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/54—Indexing scheme relating to G06F9/54
- G06F2209/548—Queue
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- General Business, Economics & Management (AREA)
- Agronomy & Crop Science (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Probability & Statistics with Applications (AREA)
- Medical Informatics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses a method for realizing remote control of a water and fertilizer integrated intelligent pump house by using cloud computing, which belongs to the technical field of control and solves the problem of remote control and self-adjustment of the water and fertilizer integrated intelligent pump house. The method comprises the steps of constructing a cloud management platform; acquiring data information of each system forming the water-fertilizer integrated intelligent pump house; processing the collected large amount of data information; intelligent management of the water and fertilizer integrated intelligent pump house according to the abnormality detection model; the method has the advantages that the virtual platform is created by applying the hybrid energy-saving algorithm in the hybrid cloud, the working report is transmitted to the multiple terminals through the self-adaptive frequency control algorithm, the water and fertilizer ratio in the pump room is regulated and controlled through the intelligent algorithm, the data information of the pump room is monitored in real time through the anomaly detection model, the technical cost and the energy consumption are greatly reduced, the safety and the confidentiality of data transmission are enhanced, and the convenience of remote control is improved.
Description
Technical Field
The invention relates to the technical field of control, in particular to a method for realizing water and fertilizer integrated intelligent pump house remote control by using cloud computing.
Background
With the deep development of the Internet +, agriculture is gradually becoming intelligent and digital. In traditional agricultural production, fertilizer and water management of farmers is generally rough, problems such as excessive or lagging fertilization, excessive or insufficient irrigation and the like can occur, resources are wasted, and land degradation and environmental pollution can be caused. The water and fertilizer integrated technology can accurately and scientifically manage the use of agricultural fertilizer and water, so that the effects of saving water, losing weight and improving yield are achieved.
In the technical system of liquid manure integration, wisdom pump house upgrades the transformation in traditional pump house, applies technologies such as sensor, data acquisition, remote control, automation to the pump house management, through the real-time supervision and the regulation and control to limiting factor, has improved the efficiency that liquid manure was used, has reduced agricultural cost, has increased the agricultural income.
In the prior art, a remote controller is adopted for control, and the specific remote control method is as follows: determining the type of a remote controller: the types of remote controllers of the water and fertilizer integrated intelligent pump house can be different from region to region, so that the types of the remote controllers used need to be determined, and common remote controller types comprise an infrared remote controller, a Bluetooth remote controller, a GPS positioning remote controller and the like. And (3) connecting a remote controller: the remote controller is connected to the controller of the water and fertilizer integrated intelligent pump room, and can be connected through a USB interface or a wireless connection mode. Operating a remote controller: the remote control is used for operation, such as selecting the start or stop of a pump house, adjusting irrigation or fertilization water level, and the like. The control capability of the method is lagged, and when the remote controller is used for controlling the water and fertilizer integrated intelligent pump house, the factors such as battery power of the remote controller, damage of the remote controller and the like need to be considered so as to ensure the safety and reliability of the operation of the pump house.
However, the water-fertilizer integrated intelligent pump house also has some drawbacks, including:
1. the technical cost is high. The water and fertilizer integrated intelligent pump house needs to cover various technologies such as sensors, data acquisition, remote control, automation and the like, and needs to optimize and integrate various technologies to enable the technologies to work cooperatively, so that the technical cost is high.
2. The requirements for the talents of the technology are high. The intelligent water-fertilizer integrated pump house needs professional technical personnel to maintain and manage the intelligent water-fertilizer integrated intelligent pump house, and the requirement on the technical personnel is large, and the operation cost is high.
3. Is greatly influenced by environmental factors. Environmental factors such as natural disasters, weather and the like can influence the water and fertilizer integrated intelligent pump house, so that the operation efficiency of the intelligent pump house is reduced.
4. The construction period is long. The water-fertilizer integrated intelligent pump house needs to make a reasonable and fine plan for each production work of a company to realize real success, the construction period is long, the water-fertilizer integrated intelligent pump house needs to be stood by, and the long-term investment return period can be long.
5. The maintenance cost is high. Intelligent agricultural projects are long-term, continuous projects that require year-round maintenance and servicing, and thus the corresponding maintenance costs are also high.
The cloud computing technology has the advantages of resource sharing, high efficiency, universality and the like, can provide functions of remote control, data storage, real-time monitoring, data analysis, intelligent decision making and the like for an intelligent pump room, realizes remote management, data analysis, real-time feedback and intelligent regulation and control, and provides more efficient, accurate and intelligent support for water and fertilizer integrated agricultural production. Therefore, cloud computing has very important significance in realizing water and fertilizer integrated intelligent pump house remote control.
Disclosure of Invention
Aiming at the defects of the technology, the invention discloses a method for realizing the remote control of a water and fertilizer integrated intelligent pump house by using cloud computing, which is characterized in that a virtual platform is created by using a hybrid energy-saving algorithm in a hybrid cloud, a working report is transmitted to a plurality of terminals by using a self-adaptive frequency control algorithm, the water and fertilizer ratio in the pump house is regulated and controlled by using the intelligent algorithm, the data information of the pump house is monitored in real time by using an anomaly detection model, the technical cost and the energy consumption are greatly reduced, the safety and the confidentiality of data transmission are enhanced, and the remote control capability is greatly improved.
In view of the above, the invention provides a method for realizing water and fertilizer integrated intelligent pump house remote control by cloud computing, which comprises the following steps,
step one, a cloud management platform is constructed;
constructing a virtual water and fertilizer integrated intelligent pump house by adopting a hybrid cloud through a hybrid energy-saving algorithm;
step two, acquiring data information of each system forming the water-fertilizer integrated intelligent pump house;
the method comprises the steps that a data collection module is adopted to obtain data and state information of all systems forming the water and fertilizer integrated intelligent pump house, the data collection module comprises a data collection unit and a system state sensing unit, the data collection unit is used for obtaining basic data information generated when all systems interact, the basic data information comprises water quantity, water pump power and water quality, and the system state sensing unit is used for obtaining working states of all systems;
step three, processing a large amount of collected data information;
processing the acquired data information by adopting a data processing module;
step four, performing anomaly detection analysis on the ordered data information;
carrying out anomaly prediction on the data information by adopting an anomaly detection model through an anomaly analysis module;
step five, intelligently managing the water and fertilizer integrated intelligent pump house according to the abnormality detection model;
the intelligent management module comprises a main controller, a management unit, a display unit, a remote interaction unit and a wireless transmission unit, wherein the main controller is used for controlling the working state of each module, the management unit regulates and controls the water-fertilizer ratio in the pump room by adopting an intelligent algorithm, the display unit is used for displaying the working state of the virtual water-fertilizer integrated intelligent pump room and monitoring reports, the wireless transmission unit transmits the generated reports to a plurality of terminals by adopting a self-adaptive frequency control algorithm, the remote interaction unit is used for remotely regulating and controlling the working state and fault maintenance of the water-fertilizer integrated intelligent pump room, the output end of the management unit is connected with the input end of the display unit, and the output end of the display unit is connected with the input end of the wireless transmission unit.
As a further description of the above technical solution, the anomaly detection model includes an anomaly data feature extraction unit, a learning training unit and a prediction analysis unit, where the anomaly data feature extraction unit is used to extract features of anomaly data information, the learning training unit iteratively trains the obtained features of anomaly data information in a neural network to obtain an optimal weight value, the prediction analysis unit is used to detect the obtained data information in real time, an output end of the anomaly data feature extraction unit is connected with an input end of the learning training unit, and an output end of the learning training unit is connected with an input end of the prediction analysis unit.
As a further description of the above technical solution, the abnormal data feature extraction unit classifies the data according to the normal and abnormal data, then performs linear discriminant analysis on each data class, performs singular value decomposition on each wavelet component, and finally uses the result output by the linear discriminant analysis as the input of the singular value decomposition, thereby obtaining deep feature information.
As a further description of the above technical solution, the learning training unit includes:
3×3 and 5×5 depth separation convolutions and 1×1 point convolutions;
more than 5 index modules consisting of 1×3, 3×1 and 1×1 convolution blocks; wherein the acceptance module includes a BN layer and a3 x 3 pooling layer;
the working method of the learning training unit comprises the following steps: and adopting feature mapping obtained by normalization layer processing, classifying by adopting an inverse residual error structure and a linear structure which are combined by 3 multiplied by 3 and 1 multiplied by 1, and finally improving training performance by a combined activation function, wherein the combined activation function is as follows:
（1）
in the formula (1), n is the stacking number,for scaling parameters, ++>For bias parameter +.>For the original activation function, x is the input data, < ->Is a super parameter.
As further description of the technical scheme, the hybrid distributed algorithm firstly utilizes MPI message passing to process calculation tasks, utilizes large-scale storage and parallel processing capacity provided by Hadoop, simultaneously utilizes memory calculation characteristics of Spark to process huge data volume, then realizes cooperation among calculation nodes through MPI, and finally processes distributed calculation and Hadoop to store data through Spark.
As further description of the technical scheme, the intelligent algorithm firstly randomly generates a group of individuals to form a first generation group, searches for an optimal position, an optimal solution and an optimal individual by utilizing a self-adaptive function, then performs crossover and mutation operations on the excellent individuals to generate new individuals, selects the new individuals meeting the optimization target by comparing the new individuals with the original group so as to update the group, and finally outputs the optimal solution when the termination criterion is reached.
As a further description of the above technical solution, the adaptive frequency control algorithm first sets an interference threshold in a normal frequency, and a probability formula that the interference of any frequency point is greater than the interference threshold is:
(2)
in the formula (2), Q represents the probability of being greater than an interference threshold, t represents the average time of congestion state, s represents the frequency point smaller than the interference threshold, and r represents the frequency point greater than the interference threshold;
the number of abnormal frequencies occurring in the normal frequencies is:
(3)
in the formula (3), the amino acid sequence of the compound,indicating normal frequency +.>Indicating the ith hop, M indicating all hop counts, E indicating the average number of abnormal frequencies, +.>Representing the duty ratio of the abnormal frequency hops in all the frequency hops;
further simplified as: （4）
in the formula (4), the amino acid sequence of the compound,representing the probability of normal frequency state +.>Representing the probability of abnormal frequency state>Representing the number of all frequencies>Representing the number of abnormal frequencies;
thus obtaining the final bit error rate as:
（5）
in the formula (5), the amino acid sequence of the compound,representing an abnormal frequency bit error rate, ">Representing the alternative frequency.
As a further description of the above technical solution, the data processing module includes a cleaning unit, a denoising unit, a storage unit and a sorting unit, where the cleaning unit performs missing searching on collected data information and fills missing parts through a hybrid distributed algorithm, the denoising unit is used for repairing abnormal parts of the data information, the sorting unit sorts the data information according to time, the storage unit stores the sorted data information in a distributed manner, an output end of the cleaning unit is connected with an input end of the denoising unit, an output end of the denoising unit is connected with an input end of the sorting unit, and an output end of the sorting unit is connected with an input end of the storage unit.
As a further description of the above technical solution, the working mode of the hybrid energy-saving algorithm is as follows: firstly, the load condition of each node of the current system is collected through server resource monitoring, the global resource condition of the system is mastered, then, tasks are reasonably distributed to nodes with idle resources or lighter loads by a load balancing algorithm based on the load condition, the utilization modes of virtual machines and memories are optimized, the scheduling of the tasks is optimized by combining the principle of load balancing, the condition that a single virtual machine is excessively slow in load or excessively heavy in load is avoided, and finally, hardware optimization is carried out on each server node.
As further description of the technical scheme, the main controller comprises an FPGA+DSP processing module, the DSP processing module is an acquisition chip of ATMega328 model, the DSP processing module integrates 14 paths of GPIO interfaces, 6 paths of PWM interfaces, 12-bit ADC interfaces, UART serial ports, 1 path of SPI interfaces and 1 path of I2C interfaces, and the FPGA processing module is a Spartan-7 series XC7S15-2CSGA225I chip.
The invention has the beneficial technical effects that compared with the prior art:
the invention discloses a method for realizing water and fertilizer integrated intelligent pump house remote control by using cloud computing, which comprises the steps of creating a virtual platform by using a hybrid energy-saving algorithm in a hybrid cloud, transmitting a work report to a plurality of terminals by using a self-adaptive frequency control algorithm, regulating and controlling the water and fertilizer ratio in a pump house by using the intelligent algorithm, and monitoring the data information of the pump house in real time by using an anomaly detection model, thereby greatly reducing the technical cost and energy consumption, enhancing the safety and confidentiality of data transmission and improving the convenience of remote control.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described below, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings may be obtained from these drawings without inventive faculty for a person skilled in the art, wherein,
figure 1 is a flow chart of the present invention,
figure 2 is a block diagram of the modules employed in the present invention,
figure 3 is a diagram of an anomaly detection model architecture,
figure 4 is a diagram of a data processing module architecture,
fig. 5 is a schematic diagram of an intelligent management module.
Detailed Description
The following description of the embodiments of the present disclosure will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the disclosure. It should be understood that the description is only illustrative and is not intended to limit the scope of the invention. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the present invention.
As shown in fig. 1-5, a method for realizing remote control of a water and fertilizer integrated intelligent pump house by using cloud computing comprises the following steps,
step one, a cloud management platform is constructed;
constructing a virtual water and fertilizer integrated intelligent pump house by adopting a hybrid cloud through a hybrid energy-saving algorithm;
step two, acquiring data information of each system forming the water-fertilizer integrated intelligent pump house;
the method comprises the steps that a data collection module is adopted to obtain data and state information of all systems forming the water and fertilizer integrated intelligent pump house, the data collection module comprises a data collection unit and a system state sensing unit, the data collection unit is used for obtaining basic data information generated when all systems interact, the basic data information comprises water quantity, water pump power and water quality, and the system state sensing unit is used for obtaining working states of all systems;
step three, processing a large amount of collected data information;
processing the acquired data information by adopting a data processing module;
step four, performing anomaly detection analysis on the ordered data information;
carrying out anomaly prediction on the data information by adopting an anomaly detection model through an anomaly analysis module;
step five, intelligently managing the water and fertilizer integrated intelligent pump house according to the abnormality detection model;
the intelligent management module comprises a main controller, a management unit, a display unit, a remote interaction unit and a wireless transmission unit, wherein the main controller is used for controlling the working state of each module, the management unit regulates and controls the water-fertilizer ratio in the pump room by adopting an intelligent algorithm, the display unit is used for displaying the working state of the virtual water-fertilizer integrated intelligent pump room and monitoring reports, the wireless transmission unit transmits the generated reports to a plurality of terminals by adopting a self-adaptive frequency control algorithm, the remote interaction unit is used for remotely regulating and controlling the working state and fault maintenance of the water-fertilizer integrated intelligent pump room, the output end of the management unit is connected with the input end of the display unit, and the output end of the display unit is connected with the input end of the wireless transmission unit.
The output end of the main controller is respectively connected with the input ends of the hybrid cloud, the data collection module, the data processing module, the anomaly analysis module and the intelligent management module, the output end of the data collection module is connected with the input end of the data processing module, the output end of the data processing module is connected with the input end of the anomaly analysis module, the output end of the anomaly analysis module is connected with the input end of the intelligent management module, and the output end of the intelligent management module is connected with the input end of the hybrid cloud.
Further, the anomaly detection model comprises an anomaly data feature extraction unit, a learning training unit and a prediction analysis unit, wherein the anomaly data feature extraction unit is used for extracting the features of anomaly data information, the learning training unit is used for carrying out iterative training on the acquired anomaly data information features in a neural network to acquire an optimal weight value, the prediction analysis unit is used for detecting the acquired data information in real time, the output end of the anomaly data feature extraction unit is connected with the input end of the learning training unit, the output end of the learning training unit is connected with the input end of the prediction analysis unit,
the working principle of the abnormality detection model is as follows: the method comprises the steps of preprocessing original data, converting the original data into representative feature vectors, establishing an abnormality detection model suitable for a data set according to a selected algorithm or method, training the data set by knowing a normal data set, adjusting parameters in the model to adapt to the definition of the normal data set, inputting test data into the trained model, and judging whether the test data belongs to the normal data set or not by the model. If the test data does not belong to the normal data set, it is determined as abnormal data, and the detected abnormal data is processed. If the abnormal data is effective data, corresponding processing measures are needed to repair the abnormal data; if the exception data is garbage, it may be culled.
Further, the abnormal data feature extraction unit classifies the data according to the normal and abnormal data, performs linear discriminant analysis on each data category, performs singular value decomposition on each wavelet component, and finally uses the result output by the linear discriminant analysis as the input of the singular value decomposition, thereby obtaining deep feature information.
Further, the learning training unit includes:
3×3 and 5×5 depth separation convolutions and 1×1 point convolutions;
more than 5 index modules consisting of 1×3, 3×1 and 1×1 convolution blocks; wherein the acceptance module includes a BN layer and a3 x 3 pooling layer;
the working method of the learning training unit comprises the following steps:
and adopting feature mapping obtained by normalization layer processing, classifying by adopting an inverse residual error structure and a linear structure which are combined by 3 multiplied by 3 and 1 multiplied by 1, and finally improving training performance by a combined activation function, wherein the combined activation function is as follows:
（1）
in the formula (1), n is the stacking number,for scaling parameters, ++>For bias parameter +.>For the original activation function, x is the input data, < ->Is the parameter of the ultrasonic wave to be used as the ultrasonic wave,
the working principle of the learning training unit is as follows: the input image 224×224×3 is feature-extracted and then changed into a feature map 112×112×32, then changed into a depth feature map 28×28×32 by an index module, then transformed into a depth feature map 7×7×320 by an inverse residual structure and a linear structure, and finally unfolded into a depth feature map 1×1×1280 by a flattening layer and a combined activation function, as shown in table 1.
TABLE 1 feature mapping table
As can be seen from table 1, the dimension is first up-scaled by 1x1 convolution, and its dimension is unchanged by deep separation convolution, and the number of channels is unchanged after passing through the reception module. Finally, the dimension reduction processing is carried out through 1x1 convolution. The number of channels after the dimension reduction corresponds to the number given by the output. For the short-cut branches of the inverted residual structure and the linear structure, the step pitch of the depth separation convolution is 1, and the number of input channels and the number of output channels are equal, so that the inverted residual structure and the linear structure are connected.
Furthermore, the hybrid distributed algorithm firstly utilizes MPI message passing to process calculation tasks, utilizes large-scale storage and parallel processing capability provided by Hadoop, simultaneously utilizes memory calculation characteristics of Spark to process huge data volume, then realizes cooperation among calculation nodes through MPI, finally processes distributed calculation and Hadoop to store data through Spark,
the principle of the hybrid distributed algorithm is as follows: in the initial stage, the centralized algorithm collects and integrates the data stored by each distributed node at the central node, and uniformly processes the data. However, in large-scale or complex tasks, the centralized algorithm may not reliably reach the goal, at which time a de-centralized algorithm needs to be introduced to allow each distributed node to perform autonomous computation, and the distributed algorithm needs to distribute tasks among each node to minimize task completion time or load balance. The centralized algorithm can directly distribute tasks according to a predefined strategy, the decentralization algorithm needs negotiation among all nodes, the task distribution is determined through a consensus algorithm (such as Paxos or Raft), and the distributed algorithm needs to ensure information synchronization among all nodes so as to ensure task completion and merging results. At the same time, the algorithm needs to avoid over-synchronization to minimize communication costs. Hybrid distributed algorithms often employ asynchronous communications (e.g., message queues) and periodic communications (e.g., heartbeat) to reduce communication overhead, and after tasks are completed, the centralized algorithm may collect results directly and combine them. However, since the de-centering algorithm may produce multiple results, the algorithm needs to combine the results eventually by a consistency algorithm (e.g., gossip or Bayou).
Further, the intelligent algorithm firstly randomly generates a group of individuals to form a first generation group, searches the optimal position, the optimal solution and the optimal individuals by utilizing the self-adaptive function, then performs crossover and mutation operation on the excellent individuals to generate new individuals, selects the new individuals meeting the optimization target by comparing the new individuals with the original group so as to update the group, finally, outputs the optimal solution when the termination criterion is reached,
the working principle of the intelligent algorithm is as follows: the double wolf algorithm and the bee colony algorithm are alternately executed in the early stage of the algorithm by a randomly generated population initialization algorithm to try to find a better solution. The double wolf algorithm explores a solution space through competition and cooperation, the bee colony algorithm cooperates through information communication and task allocation, and a genetic algorithm is introduced to accelerate a searching process in the middle and later stages of the algorithm. The algorithm evolves population through the intersection and variation among individuals, and performs the win-win elimination according to the fitness function, and in the final stage of the algorithm, all solutions are scanned once to ensure that the optimal solution is found, and by combining the advantages of three optimization algorithms, the overall optimal solution can be found in a short time. As shown in table 2.
Table 2 Intelligent optimization table
As can be seen from table 2, compared with the time consumed by optimizing the nodes by different algorithms, the time consumed by the intelligent algorithm is shorter, the optimal solution is less prone to be trapped in the local optimal solution, gradient elimination and decline, the mode of randomly initializing other single algorithms to generate the initial population cannot ensure better population diversity, the later convergence speed is low, the precision is low, the intelligent algorithm is sensitive to parameters, and the intelligent algorithm has the advantages of high convergence speed, high precision, less parameter quantity and small calculated quantity.
Further, the adaptive frequency control algorithm firstly sets an interference threshold in the normal frequency, and the probability formula that the interference of any frequency point is greater than the interference threshold is:
(2)
in the formula (2), Q represents the probability of being greater than an interference threshold, t represents the average time of congestion state, s represents the frequency point smaller than the interference threshold, and r represents the frequency point greater than the interference threshold;
the number of abnormal frequencies occurring in the normal frequencies is:
(3)
in the formula (3), the amino acid sequence of the compound,indicating normal frequency +.>Indicating the ith hop, M indicating all hop counts, E indicating the average number of abnormal frequencies, +.>Representing the duty ratio of the abnormal frequency hops in all the frequency hops;
further simplified as: （4）
in the formula (4), the amino acid sequence of the compound,representing positiveConstant frequency state probability>Representing the probability of abnormal frequency state>Representing the number of all frequencies>Representing the number of abnormal frequencies;
thus obtaining the final bit error rate as:
（5）
in the formula (5), the amino acid sequence of the compound,representing an abnormal frequency bit error rate, ">Representing the alternative frequency.
The working principle of the self-adaptive frequency control algorithm is as follows: first, the adaptive frequency control algorithm selects a modulation scheme suitable for the current communication environment, which is usually a slower modulation scheme. In the data transmission process, the self-adaptive frequency control algorithm can continuously monitor the channel quality so as to grasp the condition of the current communication environment. The measurement of channel quality is typically performed by measuring the bit error rate of the data. Based on the monitored channel quality, the adaptive frequency control algorithm selects an optimal modulation scheme according to a preset rule. If the channel quality is good, the adaptive frequency control algorithm selects a faster modulation scheme to achieve higher speed. If the channel quality is poor, the algorithm automatically reduces the modulation mode to reduce the error rate so as to ensure the correctness of data transmission. During data transmission, the adaptive frequency control algorithm continuously monitors channel quality and updates the modulation scheme as needed. In general, the algorithm will first select an appropriate modulation scheme and then adjust the rate within the range of that modulation scheme. If the discovery rate is too slow or too fast, the algorithm automatically updates the modulation scheme based on the change in channel quality, as shown in Table 3.
Table 3 frequency point hopping table
As can be seen from table 3, the frequency channels represent the positions of the frequency points listed in the frequency point hopping table of the frequency channel in the corresponding working communication channels of the original rf transceiver module. The number of the first column indicates the number position of the selected bin in the table. The frequency represents the operating communication channel in which the selected ones of the frequency points are located.
Further, the data processing module comprises a cleaning unit, a denoising unit, a storage unit and a sequencing unit, wherein the cleaning unit is used for checking the collected data information through a mixed distributed algorithm and filling the missing part, the denoising unit is used for repairing the data information abnormal part, the sequencing unit is used for sequencing the data information according to time, the storage unit is used for storing the sequenced data information in a distributed mode, the output end of the cleaning unit is connected with the input end of the denoising unit, the output end of the denoising unit is connected with the input end of the sequencing unit, and the output end of the sequencing unit is connected with the input end of the storage unit.
Further, the working mode of the hybrid energy-saving algorithm is as follows: firstly, the load condition of each node of the current system is collected through server resource monitoring, the global resource condition of the system is mastered, then, tasks are reasonably distributed to nodes with idle resources or lighter loads by a load balancing algorithm based on the load condition, the utilization modes of virtual machines and memories are optimized, the scheduling of the tasks is optimized by combining the principle of load balancing, the condition that a single virtual machine is excessively slow in load or excessively heavy in load is avoided, and finally, hardware optimization is carried out on each server node.
The working principle of the hybrid energy-saving algorithm is as follows: monitoring of the energy consumption of the data center is needed first. The monitoring typically includes real-time monitoring and recording of energy consumption by servers, network devices, storage devices, etc. Classifying, screening and de-duplication operations on data, etc., to avoid useless data operations and waste of energy. And predicting future energy consumption conditions by using a prediction model according to historical electricity utilization records, performance monitoring and other factors of the data center. On the basis of energy consumption prediction, the hybrid energy-saving algorithm controls energy consumption according to the prediction result by utilizing related energy control strategies such as acceleration and deceleration calculation, dynamic increase or decrease of server and storage capacity and the like. According to the real-time state and the energy consumption prediction result of the data center, more accurate and dynamic energy control is performed, so that the energy utilization efficiency is improved while the excessive consumption of energy is avoided and the service quality is ensured.
Further, the main controller comprises an FPGA+DSP processing module, the DSP processing module is an acquisition chip of ATMega328 model, the DSP processing module integrates a 14-path GPIO interface, a 6-path PWM interface, a 12-bit ADC interface, a UART serial port, a 1-path SPI interface and a 1-path I2C interface, the FPGA processing module is a Spartan-7 series XC7S15-2CSGA225I chip,
the working process of the main controller is as follows: the main controller firstly controls the data collection module to acquire data and state information of all systems forming the water and fertilizer integrated intelligent pump house and reflect the data and state information in the mixed cloud to construct a virtual water and fertilizer integrated intelligent pump house, then controls the data processing module to clean, denoise, store and sort the acquired data information, then controls the abnormality analysis module to monitor the data information acquired in real time, finally controls the intelligent management module to convert management daily into a form of a graphic form to be transmitted to a plurality of terminals through wireless transmission, and realizes the remote control process of the water and fertilizer integrated intelligent pump house through remote interaction.
While specific embodiments of the present invention have been described above, it will be understood by those skilled in the art that these specific embodiments are by way of example only, and that various omissions, substitutions, and changes in the form and details of the methods and systems described above may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the above-described method steps to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is limited only by the following claims.
Claims (10)
1. A method for realizing remote control of a water and fertilizer integrated intelligent pump house by using cloud computing is characterized by comprising the following steps: comprises the following steps of the method,
step one, a cloud management platform is constructed;
constructing a virtual water and fertilizer integrated intelligent pump house by adopting a hybrid cloud through a hybrid energy-saving algorithm;
step two, acquiring data information of each system forming the water-fertilizer integrated intelligent pump house;
the method comprises the steps that a data collection module is adopted to obtain data and state information of all systems forming the water and fertilizer integrated intelligent pump house, the data collection module comprises a data collection unit and a system state sensing unit, the data collection unit is used for obtaining basic data information generated when all systems interact, the basic data information comprises water quantity, water pump power and water quality, and the system state sensing unit is used for obtaining working states of all systems;
step three, processing a large amount of collected data information;
processing the acquired data information by adopting a data processing module;
step four, performing anomaly detection analysis on the ordered data information;
carrying out anomaly prediction on the data information by adopting an anomaly detection model through an anomaly analysis module;
step five, intelligently managing the water and fertilizer integrated intelligent pump house according to the abnormality detection model;
the intelligent management module comprises a main controller, a management unit, a display unit, a remote interaction unit and a wireless transmission unit, wherein the main controller is used for controlling the working state of each module, the management unit regulates and controls the water-fertilizer ratio in the pump room by adopting an intelligent algorithm, the display unit is used for displaying the working state of the virtual water-fertilizer integrated intelligent pump room and monitoring reports, the wireless transmission unit transmits the generated reports to a plurality of terminals by adopting a self-adaptive frequency control algorithm, the remote interaction unit is used for remotely regulating and controlling the working state and fault maintenance of the water-fertilizer integrated intelligent pump room, the output end of the management unit is connected with the input end of the display unit, and the output end of the display unit is connected with the input end of the wireless transmission unit.
2. The method for realizing the remote control of the water and fertilizer integrated intelligent pump house by using cloud computing according to claim 1, which is characterized by comprising the following steps: the abnormal detection model comprises an abnormal data feature extraction unit, a learning training unit and a prediction analysis unit, wherein the abnormal data feature extraction unit is used for extracting features of abnormal data information, the learning training unit is used for carrying out iterative training on the acquired abnormal data information features in a neural network to acquire optimal weight values, the prediction analysis unit is used for detecting the acquired data information in real time, the output end of the abnormal data feature extraction unit is connected with the input end of the learning training unit, and the output end of the learning training unit is connected with the input end of the prediction analysis unit.
3. The method for realizing the remote control of the water and fertilizer integrated intelligent pump house by using cloud computing according to claim 2, which is characterized by comprising the following steps: the abnormal data feature extraction unit classifies data according to normal and abnormal, performs linear discriminant analysis on each data category, performs singular value decomposition on each wavelet component, and finally takes the result output by the linear discriminant analysis as the input of the singular value decomposition, thereby obtaining deep feature information.
4. The method for realizing the remote control of the water and fertilizer integrated intelligent pump house by using cloud computing according to claim 2, which is characterized by comprising the following steps: the learning training unit includes:
3×3 and 5×5 depth separation convolutions and 1×1 point convolutions;
more than 5 index modules consisting of 1×3, 3×1 and 1×1 convolution blocks; wherein the acceptance module includes a BN layer and a3 x 3 pooling layer;
the working method of the learning training unit comprises the following steps:
and adopting feature mapping obtained by normalization layer processing, classifying by adopting an inverse residual error structure and a linear structure which are combined by 3 multiplied by 3 and 1 multiplied by 1, and finally improving training performance by a combined activation function, wherein the combined activation function is as follows:
（1）
in the formula (1), n is the stacking number,for scaling parameters, ++>For bias parameter +.>For the original activation function, x is the input data, < ->Is a super parameter.
5. The method for realizing the remote control of the water and fertilizer integrated intelligent pump house by using cloud computing according to claim 1, which is characterized by comprising the following steps: the data processing module comprises a cleaning unit, a denoising unit, a storage unit and a sequencing unit, wherein the cleaning unit is used for checking the collected data information through a mixed distributed algorithm and filling the missing part, the denoising unit is used for repairing the data information abnormal part, the sequencing unit is used for sequencing the data information according to time, the storage unit is used for storing the sequenced data information in a distributed mode, the output end of the cleaning unit is connected with the input end of the denoising unit, the output end of the denoising unit is connected with the input end of the sequencing unit, and the output end of the sequencing unit is connected with the input end of the storage unit.
6. The method for realizing the remote control of the water and fertilizer integrated intelligent pump house by using cloud computing according to claim 5, which is characterized in that: the hybrid distributed algorithm firstly utilizes MPI message transmission to process calculation tasks, utilizes large-scale storage and parallel processing capacity provided by Hadoop, simultaneously utilizes memory calculation characteristics of Spark to process huge data volume, then realizes cooperation among calculation nodes through MPI, and finally processes distributed calculation and Hadoop to store data through Spark.
7. The method for realizing the remote control of the water and fertilizer integrated intelligent pump house by using cloud computing according to claim 1, which is characterized by comprising the following steps: the intelligent algorithm firstly randomly generates a group of individuals to form a first generation group, searches the optimal position, the optimal solution and the optimal individuals by utilizing the self-adaptive function, then performs crossover and mutation operations on the excellent individuals to generate new individuals, selects the new individuals meeting the optimization target through comparison of the new individuals and the original group so as to update the group, and finally outputs the optimal solution when the termination criterion is reached.
8. The method for realizing the remote control of the water and fertilizer integrated intelligent pump house by using cloud computing according to claim 1, which is characterized by comprising the following steps: the working method of the self-adaptive frequency control algorithm comprises the following steps:
setting an interference threshold in normal frequency, wherein the probability formula of the interference of any frequency point being larger than the interference threshold is as follows:
(2)
in the formula (2), Q represents the probability of being greater than an interference threshold, t represents the average time of congestion state, s represents the frequency point smaller than the interference threshold, and r represents the frequency point greater than the interference threshold;
the number of abnormal frequencies occurring in the normal frequencies is:
(3)
in the formula (3), the amino acid sequence of the compound,indicating normal frequency +.>Indicating the ith hop, M indicating all hop counts, E indicating the average number of abnormal frequencies, +.>Representing the duty ratio of the abnormal frequency hops in all the frequency hops;
the number of abnormal frequencies is further simplified as:
（4）
in the formula (4), the amino acid sequence of the compound,representing the probability of normal frequency state +.>Representing the probability of abnormal frequency state>Representing the number of all frequencies>Representing the number of abnormal frequencies;
thus obtaining the final bit error rate as:
（5）
in the formula (5), the amino acid sequence of the compound,representing an abnormal frequency bit error rate, ">Representing the alternative frequency.
9. The method for realizing the remote control of the water and fertilizer integrated intelligent pump house by using cloud computing according to claim 1, which is characterized by comprising the following steps: the working mode of the hybrid energy-saving algorithm is as follows: firstly, the load condition of each node of the current system is collected through server resource monitoring, the global resource condition of the system is mastered, then, tasks are reasonably distributed to nodes with idle resources or lighter loads by a load balancing algorithm based on the load condition, the utilization modes of virtual machines and memories are optimized, the scheduling of the tasks is optimized by combining the principle of load balancing, the condition that a single virtual machine is excessively slow in load or excessively heavy in load is avoided, and finally, hardware optimization is carried out on each server node.
10. The method for realizing the remote control of the water and fertilizer integrated intelligent pump house by using cloud computing according to claim 1, which is characterized by comprising the following steps: the main controller comprises an FPGA+DSP processing module, the DSP processing module is an acquisition chip of ATMega328 model, the DSP processing module integrates a 14-path GPIO interface, a 6-path PWM interface, a 12-bit ADC interface, a UART serial port, a 1-path SPI interface and a 1-path I2C interface, and the FPGA processing module is a Spartan-7 series XC7S15-2CSGA225I chip.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310903920.3A CN116647586A (en) | 2023-07-24 | 2023-07-24 | Method for realizing remote control of water and fertilizer integrated intelligent pump house by cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310903920.3A CN116647586A (en) | 2023-07-24 | 2023-07-24 | Method for realizing remote control of water and fertilizer integrated intelligent pump house by cloud computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116647586A true CN116647586A (en) | 2023-08-25 |
Family
ID=87623319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310903920.3A Pending CN116647586A (en) | 2023-07-24 | 2023-07-24 | Method for realizing remote control of water and fertilizer integrated intelligent pump house by cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116647586A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118413523A (en) * | 2024-07-02 | 2024-07-30 | 问策师信息科技南京有限公司 | Method for realizing computer network information remote control by using cloud computing |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106125701A (en) * | 2016-08-26 | 2016-11-16 | 山东锋士信息技术有限公司 | Cloud system is irrigated to wisdom based on internet liquid manure management equipment |
| CN106171866A (en) * | 2016-08-26 | 2016-12-07 | 山东锋士信息技术有限公司 | Internet-based smart irrigation cloud platform |
| CN107704545A (en) * | 2017-11-08 | 2018-02-16 | 华东交通大学 | Railway distribution net magnanimity information method for stream processing based on Storm Yu Kafka message communicatings |
| CN110187688A (en) * | 2019-06-14 | 2019-08-30 | 青岛农业大学 | Industrialized agriculture intelligence liquid manure integral control system and control method |
| CN111272218A (en) * | 2020-01-21 | 2020-06-12 | 奥利机械(集团)有限公司 | Integrated intelligent pump room management system based on VR environment |
| CN211557995U (en) * | 2019-11-29 | 2020-09-25 | 洛阳中科龙网创新科技有限公司 | Remote intelligent measurement and control water and fertilizer integrated machine control system |
| CN111898669A (en) * | 2020-07-24 | 2020-11-06 | 大连重工机电设备成套有限公司 | Machine learning-based direct-current submerged arc furnace abnormal event early warning system |
| CN112099425A (en) * | 2020-01-10 | 2020-12-18 | 上海遂志机电有限公司 | Wisdom pump house system |
| CN112450056A (en) * | 2019-09-09 | 2021-03-09 | 云南天质弘耕科技有限公司 | Water, fertilizer and pesticide integrated intelligent irrigation system based on machine learning algorithm |
| CN112527604A (en) * | 2020-12-16 | 2021-03-19 | 广东昭阳信息技术有限公司 | Deep learning-based operation and maintenance detection method and system, electronic equipment and medium |
| CN113962299A (en) * | 2021-10-15 | 2022-01-21 | 上海核工程研究设计院有限公司 | Intelligent operation monitoring and fault diagnosis general model for nuclear power equipment |
| CN115094976A (en) * | 2022-07-13 | 2022-09-23 | 山东工泵电机有限公司 | Water and fertilizer integrated intelligent pump house system |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN116360331A (en) * | 2023-06-02 | 2023-06-30 | 山东工泵电机有限公司 | Universal automatic control system and control method |
-
2023
- 2023-07-24 CN CN202310903920.3A patent/CN116647586A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106171866A (en) * | 2016-08-26 | 2016-12-07 | 山东锋士信息技术有限公司 | Internet-based smart irrigation cloud platform |
| CN106125701A (en) * | 2016-08-26 | 2016-11-16 | 山东锋士信息技术有限公司 | Cloud system is irrigated to wisdom based on internet liquid manure management equipment |
| CN107704545A (en) * | 2017-11-08 | 2018-02-16 | 华东交通大学 | Railway distribution net magnanimity information method for stream processing based on Storm Yu Kafka message communicatings |
| CN110187688A (en) * | 2019-06-14 | 2019-08-30 | 青岛农业大学 | Industrialized agriculture intelligence liquid manure integral control system and control method |
| CN112450056A (en) * | 2019-09-09 | 2021-03-09 | 云南天质弘耕科技有限公司 | Water, fertilizer and pesticide integrated intelligent irrigation system based on machine learning algorithm |
| CN211557995U (en) * | 2019-11-29 | 2020-09-25 | 洛阳中科龙网创新科技有限公司 | Remote intelligent measurement and control water and fertilizer integrated machine control system |
| CN112099425A (en) * | 2020-01-10 | 2020-12-18 | 上海遂志机电有限公司 | Wisdom pump house system |
| CN111272218A (en) * | 2020-01-21 | 2020-06-12 | 奥利机械(集团)有限公司 | Integrated intelligent pump room management system based on VR environment |
| CN111898669A (en) * | 2020-07-24 | 2020-11-06 | 大连重工机电设备成套有限公司 | Machine learning-based direct-current submerged arc furnace abnormal event early warning system |
| CN112527604A (en) * | 2020-12-16 | 2021-03-19 | 广东昭阳信息技术有限公司 | Deep learning-based operation and maintenance detection method and system, electronic equipment and medium |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN113962299A (en) * | 2021-10-15 | 2022-01-21 | 上海核工程研究设计院有限公司 | Intelligent operation monitoring and fault diagnosis general model for nuclear power equipment |
| CN115094976A (en) * | 2022-07-13 | 2022-09-23 | 山东工泵电机有限公司 | Water and fertilizer integrated intelligent pump house system |
| CN116360331A (en) * | 2023-06-02 | 2023-06-30 | 山东工泵电机有限公司 | Universal automatic control system and control method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118413523A (en) * | 2024-07-02 | 2024-07-30 | 问策师信息科技南京有限公司 | Method for realizing computer network information remote control by using cloud computing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117036104B (en) | Intelligent electricity utilization method and system based on electric power Internet of things | |
| CN114742294A (en) | Neural network algorithm for carbon emission prediction | |
| CN113259469B (en) | Edge server deployment method, system and storage medium in intelligent manufacturing | |
| CN116647586A (en) | Method for realizing remote control of water and fertilizer integrated intelligent pump house by cloud computing | |
| CN110212551B (en) | Micro-grid reactive power automatic control method based on convolutional neural network | |
| CN114358473A (en) | Multi-station integrated energy supply system | |
| CN113452033A (en) | Method for controlling voltage of high-proportion photovoltaic power distribution network with partition autonomy and storage medium | |
| CN115392340A (en) | Power load prediction system and prediction method for multi-energy electric propulsion ship | |
| Huang et al. | Smart energy management system based on reconfigurable AI chip and electrical vehicles | |
| CN115514097A (en) | Village domain CPS regulation and control system and method based on distributed photovoltaic supply and demand interactive coordination control | |
| CN118232343A (en) | Charging and discharging dynamic control method and system based on wind energy prediction | |
| CN116739187B (en) | Reservoir optimal scheduling decision method, device, computer equipment and storage medium | |
| CN117728395A (en) | Micro-grid networking interconnection and flexible switching strategy system and method | |
| CN116885840A (en) | Distributed new energy online monitoring method and system based on real-time data | |
| CN116614195A (en) | Electric carbon calculation intelligent fusion terminal based on edge container and time synchronization method | |
| CN116170881A (en) | Cross-domain resource allocation and unloading method and system based on edge calculation | |
| CN116244875A (en) | Virtual power plant cluster division method and device | |
| CN113887892B (en) | Interactive control method for plug-and-play terminal of distributed power supply | |
| CN113258606B (en) | Intelligent micro-grid energy management system based on artificial intelligence | |
| CN115224743A (en) | Distribution network scheduling management method based on energy interconnection | |
| Balaji et al. | Energy prediction in IoT systems using machine learning models | |
| CN113673141A (en) | Energy router modeling and optimization control method based on data driving | |
| CN113947321A (en) | Distributed information energy network topological structure construction method and system | |
| CN113934175A (en) | Intelligent wireless steam turbine data acquisition system | |
| CN111709589A (en) | Community energy efficiency management method and device and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230825 |