CN110501983A - Expert control system and control method based on batch seed-coating machine - Google Patents
Expert control system and control method based on batch seed-coating machine Download PDFInfo
- Publication number
- CN110501983A CN110501983A CN201910698404.5A CN201910698404A CN110501983A CN 110501983 A CN110501983 A CN 110501983A CN 201910698404 A CN201910698404 A CN 201910698404A CN 110501983 A CN110501983 A CN 110501983A
- Authority
- CN
- China
- Prior art keywords
- seed
- coating machine
- expert
- drum
- module
- 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.)
- Granted
Links
- 239000011248 coating agent Substances 0.000 title claims abstract description 93
- 238000000576 coating method Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims description 14
- 238000012797 qualification Methods 0.000 claims abstract description 43
- 230000003993 interaction Effects 0.000 claims abstract description 14
- 239000003814 drug Substances 0.000 claims description 29
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 7
- 238000005303 weighing Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 229940079593 drug Drugs 0.000 claims description 5
- 238000012986 modification Methods 0.000 claims description 5
- 230000004048 modification Effects 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000007599 discharging Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000003111 delayed effect Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- 230000005611 electricity Effects 0.000 claims 1
- 238000000465 moulding Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 2
- 238000003754 machining Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012372 quality testing Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 241000607479 Yersinia pestis Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000008117 seed development Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32368—Quality control
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Pretreatment Of Seeds And Plants (AREA)
Abstract
The invention discloses a kind of expert control systems based on batch seed-coating machine, including seed-coating machine, image detecting system and expert system, expert system includes control cabinet and display screen, human-computer interaction interface is equipped in control cabinet, base module, inference engine module, feed back self-learning module and control centre, control centre is industrial personal computer, industrial personal computer is electrically bi-directionally connected human-computer interaction interface respectively, feed back the PLC control module of self-learning module and seed-coating machine, electrically output connects base module to the human-computer interaction interface, electrically output connects inference engine module to the feedback self-learning module, the signal input part of the feedback self-learning module is also connect with the signal output end signal of image detecting system, for receiving the coating qualification rate of image detecting system feedback.The present invention is realized for different seed Automatic Optimal Combined machining parameters, under the premise of meeting coating quality and qualification rate, is improved efficiency, is saved coating agent dosage, significant effect.
Description
Technical field
The invention belongs to seed coating technology fields, and in particular to a kind of expert control system based on batch seed-coating machine
And control method.
Background technique
Seed coating technology can effectively prevent pest and disease damage protection seed development, improve seed vitality, reduce environmental pollution, drop
Low production cost, promote increasing crop yield good harvest, have huge economy, ecological benefits, be realize seed processing machineryization and
A kind of standardized important channel of breeding, is worldwide used widely.Seed pelleting machine has last 100 years and goes through
History is quickly grown in China in recent years.The design of prior seed seed-coating machine more biases toward mechanical part, and electric-control system is using letter
Easy device, it is difficult to realize accurate control, each unit coordinates cannot be made orderly to work, also need manually to participate in, machined parameters depend on
The experience of operator seriously constrains the raising of seed pelleting quality.Although domestic seed pelleting equipment is on structural principle
By the improvement of several generations product, coating machine control system is developed as control core using PLC or chip development plate and reaches accurate control
The purpose of system, the space but control system is still greatly improved.
Expert system has obtained more and more applications in recent years, it has also become it is most active in artificial intelligence technology, most by weight
Depending on field.Currently, very few for the research of seed-coating machine expert system, Yang Wanxia etc. constructs a set of special using single-chip microcontroller as core
Family's system, achievees the purpose that precisely to be coated, but also needs in terms of knowledge acquisition, inference rule further perfect.In addition, tradition kind
The design of sub- seed-coating machine more biases toward mechanical part, and electric-control system uses easy device, also needs manually to participate in, it is difficult to realize essence
Really control, cannot make each unit coordinates orderly work, and machined parameters depend on the experience of operator, and intelligence degree is low, seriously
Constrain the raising of seed pelleting quality.Thus need to design the seed-coating machine expert system with online feedback and Intelligent Optimization
System, realizes the intelligence and precision of control.
Summary of the invention
It is an object of the invention to construct a kind of expert control system based on batch seed-coating machine, while providing corresponding
Control method realizes the intelligence and precision of seed-coating machine control.
The present invention is achieved by the following technical solutions:
A kind of expert control system based on batch seed-coating machine, including seed-coating machine and image detecting system, the coating
Machine is batch seed-coating machine, is made of medicine system, charging system, coated systems and PLC control module, and the PLC controls mould
Block is connect with medicine system, charging system and coated systems signal respectively, for controlling seed-coating machine operation；Described image detection system
System is set to the side of coated systems, and the signal input part of image detecting system and the signal output end signal of PLC control module connect
It connects, further includes expert system, expert's decorum is set to figure for detecting seed pelleting quality and Real-time Feedback coating qualification rate
As the side of detection system, including control cabinet and display screen, the display screen is installed on the front of control cabinet, in the control cabinet
Equipped with human-computer interaction interface, base module, inference engine module, feedback self-learning module and control centre, the control
Center is industrial personal computer, and the industrial personal computer is electrically bi-directionally connected human-computer interaction interface, feedback self-learning module and seed-coating machine respectively
PLC control module, electrically output connection base module, the feedback self-learning module are electrically defeated for the human-computer interaction interface
Inference engine module is connected out, and the signal input part of the feedback self-learning module is also believed with the signal output end of image detecting system
Number connection, for receive image detecting system feedback coating qualification rate.
The technical solution that the present invention further solves is that the medicine system is set to the side of coated systems, including drug storage
Bucket, loading pump and grug transportation tube；The charging system is set to the top of coated systems, including feeding chamber and feed bin；The coating system
System includes throwing disc, drum, discharge port, throwing disc motor and drum motor；One end of the grug transportation tube is located in medicine storing drum, the other end
Positioned at the top of throwing disc, grug transportation tube is pumped equipped with loading, and grug transportation tube is pumped by the loading by the coating agent for seed in medicine storing drum
It is delivered to throwing disc；The feeding chamber is located at the top of drum, and the surface of feeding chamber is feed bin, and the feed bin will by feeding chamber
Seed is put into drum；The throwing disc is located at the position that middle part is on the upper side in drum, and the lower part of throwing disc is equipped with throwing disc motor, the throwing disc
It is electrically connected with throwing disc motor, its rotation is driven by throwing disc motor control；The lower section of throwing disc motor is equipped with drum motor, the drum
It is electrically connected with drum motor, its rotation is driven by drum motor control；The discharge port is located at the side wall of drum, the end of discharge port
Portion is equipped with image detecting system；The signal output end of the PLC control module respectively with loading pump, throwing disc motor and drum motor
Signal input part connection.
The technical solution that the present invention further solves is that weighing sensor, the weighing and sensing are equipped in the feed bin
The signal input part of device is connect with the signal output end of PLC control module, for controlling the charge weight of each batch.
The technical solution that the present invention further solves is that the throwing disc and drum are the trapezoidal hollow round table in section.
The present invention also protects a kind of control method of expert control system based on batch seed-coating machine, including following specific
Step:
S1: expert system and image monitoring system start and initialize；
S2: expert system is pushed away according to coating quality target value set by user and seed characteristics by neural network model
Each machined parameters of seed-coating machine are recommended, and is confirmed or is modified by user；
S3: seed-coating machine receives the parameter of user's confirmation or modification, is coated operation；
S4: the sampling period that image detecting system is arranged according to expert system is coated quality and qualification rate to product
Detection, and Real-time Feedback optimizes to expert system for reasoning；
The further on-line training neural network model of result of S5: expert system receiving step S4 feedback, works as neural network
For accuracy rate in reasonable error, then coating of the starting based on artificial bee colony algorithm optimizes plan to model predication value in stipulated number
Slightly, otherwise return step S2 redefines each machined parameters of seed-coating machine, until actual processing result is in the reasonable neck of expectation target
Then stop optimizing in domain.
Further, in the step S2, each machined parameters of seed-coating machine be by expert system feedback self-learning module and
Inference engine module carries out fuzzy recommendation, the specific steps are as follows:
S21: meet qualification rate for expectation target and reach requirement, design multiple target cost function, multiple target cost function
Specifically: min S=α | z1|+β|M|,z1=yd-yp1；Wherein, S is evaluation function；z1For expectation and practical qualification rate deviation；
yp1For the seed qualification rate actually obtained；ydQualification rate is coated for expectation；M is pesticide-seeds ratio；It is inclined that α and β is respectively directed to qualification rate
Weight coefficient between difference and practical pesticide-seeds ratio；
S22: carrying out unified normalized to time-varying parameter, the time-varying parameter optimized and revised, and specific adjustment is public
Formula are as follows:Wherein,For original parameter value, xiFor parameter after normalization；PLiAnd PUiRespectively correspond under parameter
Boundary and the upper bound；
S23: it is inputted the time-varying parameter after step S23 normalized as neural network model, by what is actually obtained
The prediction output of neural network is arranged as output in seed qualification rate；
S24: using artificial bee colony algorithm, and parameter is allowed to adjust toward excellent directional variance, while avoiding falling into part most again
It is excellent；
S25: by each circulation feedback as a result, being coated qualification rate, return step in conjunction with the obtained expectation of step S23
Evaluation function value is calculated in S21, selects adjustment parameter according to evaluation function value.
Further, in the step S22, time-varying parameter include pesticide-seeds ratio, main motor frequency, batch duration, for medicine
Duration, pump delay are for medicine, discharge duration, pump rated power and any parameter being coated in quality.
Further, in the step S25, system takes evasion tactics, while stipulated number is arranged for parameter variation,
Limitation parameter optimization falls into endless loop.
The invention has the benefit that
The present invention devises one kind using expert system as core, including batch seed pelleting machine and the inspection of coating quality image
The intelligent control system of examining system.Using seed pelleting quality and qualification rate as target, by constructing packet neural network based
Clothing Parameter Self-learning and Intelligent Hybrid parameter optimization policy system, library and Real-time Feedback value based on experience, to seed-coating machine
Machined parameters realize on-line optimization, realize for different seed Automatic Optimal Combined machining parameters, are coated quality meeting
Under the premise of qualification rate, efficiency is improved, saves coating agent dosage, significant effect.
Detailed description of the invention
Fig. 1 is schematic structural view of the invention.
Fig. 2 is expert system connection block diagram of the invention.
Fig. 3 is expert system control flow chart of the invention.
Fig. 4 is expert system parameter optimization principle flow chart of the invention.
Fig. 5 is neural networks principles structure chart of the invention.
Serial number in figure, 1- control cabinet, 2- display screen, 3- image detecting system, 4- discharge port, 5- drum, 6- throwing disc, 7- add
Feed bin, 8- feed bin, 9- grug transportation tube, 10- loading pump, 11- medicine storing drum, 12- drum motor, 13- throwing disc motor, 14-PLC control mould
Block, 101- human-computer interaction interface, 102- base module, 103- inference engine module, 104- feed back self-learning module, 105- industry control
Machine.
Specific embodiment
Summary of the invention of the invention is further described with reference to the accompanying drawings and examples.
Referring to a kind of expert control system based on batch seed-coating machine shown in Fig. 1-2, including seed-coating machine and image inspection
Examining system 3, the seed-coating machine is batch seed-coating machine, by medicine system, charging system, coated systems and PLC control module 14
Composition, the PLC control module 14 are connect with medicine system, charging system and coated systems signal respectively, for controlling coating
Machine operation；The PLC control module 14 is mainly made of PLC component and touch screen etc., it is preferable that is selected in the present embodiment
PLC control module be SIEMENS S 7-200, therefore the operating condition in seed-coating machine is controlled by PLC control module, and passed through
PLC control module carries out the well-known technique that acquisition and monitoring of data etc. are those skilled in the art；Described image detection system
System 3 is set to the side of coated systems, and the signal input part of image detecting system 3 and the signal output end of PLC control module 14 are believed
Number connection, the image detecting system be used for seed pelleting quality testing, and Real-time Feedback coating qualification rate and coating quality,
A kind of specific structure of image detecting system seed pelleting qualification rate as disclosed in the patent document of CN201820897736.7
Detection system specifically includes feeding blanking system, image capturing system and image processing control system etc., feeding blanking system
System is made of vibrating disk, feeding guide groove, discharge guide, discharging solenoid valve and air compressor machine etc., and vibrating disk has a hopper to hold to have wrapped
Clothing seed enters detection box by feeding guide groove with sequencing sequence one one under the vibration of vibrating disk, at the end of detection, beats
Material solenoid valve is outputed, the high pressure gas of air compressor machine blows away seed, enters seed collection case by discharge guide；Described image
Acquisition system is made of 4 industrial cameras, 4 light sources, and camera and light source are arranged in detect box to be mutually on the circumference in the center of circle
90 ° of angles, when seed enters detection box, 4 cameras are taken pictures simultaneously, and image reaches image processing control system；The figure
As processing control system receive the image from industrial camera simultaneously handled and calculated, obtain every seed coating quality and
The coating qualification rate of batch of seeds, and feed back to expert system；A kind of Multimode Control based on batch seed-coating machine of the invention
System further includes expert system, and expert's decorum is set to the side of image detecting system, including control cabinet 1 and display screen 2, institute
State the front that display screen 2 is installed on control cabinet 1, be equipped in the control cabinet 1 human-computer interaction interface 101, base module 102,
Inference engine module 103, feedback self-learning module 104 and control centre；Wherein, the human-computer interaction interface, user can lead to
It crosses interface and carries out the relevant operations such as parameter setting, data query, control operation；The base module can be accessed and be managed
Expertise and experience are used for inference machine, have the function of storage, editor, retrieve, modify and expand etc.；The inference machine mould
Block decomposed by the design requirement that inputs to user, by constantly making inferences with rule condition matching；The feedback is certainly
Study module saves optimal solution for formulating suitable adjustment rule in real time；The control centre is industrial personal computer 105,
The PLC that the industrial personal computer 105 is electrically bi-directionally connected human-computer interaction interface 101 respectively, feeds back self-learning module 104 and seed-coating machine
Control module 14, electrically output connects base module 102, the feedback self-learning module 104 to the human-computer interaction interface 101
Electrically output connection inference engine module 103, it is described feedback self-learning module 104 signal input part also with image detecting system 3
Signal output end signal connection, for receive image detecting system feedback coating qualification rate.
In the present embodiment, the working principle of the expert system is, by expert system control seed-coating machine and image detection system
System operation, establishes expert system knowledge base and the reasoning principle of optimality, and realizing has the machined parameters Automatic Optimal of result feedback.In
Under the premise of guaranteeing coating quality and qualification rate, optimize machined parameters, reduce pesticide-seeds ratio and lots processed time, saves medication
Amount, improves efficiency.System passes through nerve in conjunction with kind of subtype and characteristic parameter according to the desired value of coating quality and qualification rate
Each machined parameters of network model intelligent recommendation seed-coating machine enter automatic processing program after user's confirmation or modification, according to specified ginseng
Number is coated, and obtains feedback result by image detecting system, passes through the further on-line training neural network of feedback result
Model.When accuracy rate then can star in reasonable error based on artificial Neural Network model predictive value in stipulated number
Otherwise the coating optimisation strategy of ant colony algorithm will still use rule optimization strategy, subsequently into next fabrication cycles, until
Actual processing result then stops optimizing in the reasonable field of expectation target.Neural network model can obtain always in operational process
Training.Each operating parameter and result will record in knowledge base, with increasing for knowledge base data volume, model and recommendation
Machined parameters are more accurate.
Referring to Fig. 1, in the present embodiment, the medicine system is set to the side of coated systems, including medicine storing drum 11, loading pump
10 and grug transportation tube 9, medicine storing drum 11 made by resistant material, stored seed coating agent, grug transportation tube 9 be corrosion-resistant plastic pipe；Institute
The top that charging system is set to coated systems, including feeding chamber 7 and feed bin 8 are stated, the kind of need of coating is stored in 8 inner space of feed bin
Son, when seed has lacked meeting auto feed；The coated systems include throwing disc 6, drum 5, discharge port 4, throwing disc motor 13 and drum
Motor 12；One end of the grug transportation tube 9 is located in medicine storing drum 11, and the other end is located at the top of throwing disc 6, and grug transportation tube 9 is equipped with defeated
Coating agent for seed in medicine storing drum 11 is delivered to throwing disc 6 by loading pump 10 by Teat pipette 10, grug transportation tube 9；The feeding chamber 7
Positioned at the top of drum 5, the surface of feeding chamber 7 is feed bin 8, and seed is put into drum 5 by feeding chamber 7 by the feed bin 8；Institute
It states throwing disc 6 and is located at the position that middle part is on the upper side in drum 5, the lower part of throwing disc 6 is equipped with throwing disc motor 13, and throwing disc 6 is that a section is ladder
The hollow round table of shape is connected with throwing disc motor 13, and throwing disc 6 can rotate at high speed driven by the motor, and medicament is formed after entering
Mist is mixed with seed；The lower section of throwing disc motor 13 is equipped with drum motor 12, and drum 5 is also trapezoidal hollow circle for a section
Platform is connected with drum motor 12, and drum 5 can rotate at high speed, after seed entrance under the action of the centrifugal force driven by the motor
It rotates together, and mixes completion coating with medicament；The discharge port 4 is located at the side wall of drum 5, and discharging is opened after coating
Mouthful, the seed for wrapping clothing leaves drum and is carried away, and the end of discharge port 4 is equipped with image detecting system 3, and the seed for wrapping clothing enters
In the loading plate of image detecting system, it is coated quality testing；The signal output end of the PLC control module 14 respectively with it is defeated
Teat pipette 10, throwing disc motor 13 are connected with the signal input part of drum motor 12.
In the present embodiment, weighing sensor is equipped in the feed bin 8, it is preferred that model Shenzhen China of weighing sensor
The 108BA-150Kg type of Nan Hengtai Industrial Co., Ltd., the signal input part and PLC control module 14 of the weighing sensor
Signal output end connection, when up to each batch plus when formula weight, stop blowing, when each lots processed starts, charging
Door is opened in storehouse, is put down seed and is entered drum.
The present invention also protects a kind of control method of expert control system based on batch seed-coating machine, referring to Fig. 3, including
Following specific steps:
S1: expert system and image monitoring system start and initialize；
S2: expert system is pushed away according to coating quality target value set by user and seed characteristics by neural network model
Each machined parameters of seed-coating machine are recommended, and is confirmed or is modified by user；
S3: seed-coating machine receives the parameter of user's confirmation or modification, is coated operation；
S4: the sampling period that image detecting system is arranged according to expert system is coated quality and qualification rate to product
Detection, and Real-time Feedback optimizes to expert system for reasoning；
The further on-line training neural network model of result of S5: expert system receiving step S4 feedback, works as neural network
For accuracy rate in reasonable error, then coating of the starting based on artificial bee colony algorithm optimizes plan to model predication value in stipulated number
Slightly, otherwise return step S2 redefines each machined parameters of seed-coating machine, until actual processing result is in the reasonable neck of expectation target
Then stop optimizing in domain.
Referring to fig. 4, in the present embodiment, in the step S2, each machined parameters of seed-coating machine be by expert system feedback from
Study module and inference engine module carry out fuzzy recommendation, the specific steps are as follows:
S21: meet qualification rate for expectation target and reach requirement, design multiple target cost function, multiple target cost function
Specifically: min S=α | z1|+β|M|,z1=yd-yp1；Wherein, S is evaluation function；z1For expectation and practical qualification rate deviation；
yp1For the seed qualification rate actually obtained；ydQualification rate is coated for expectation；M is pesticide-seeds ratio；It is inclined that α and β is respectively directed to qualification rate
Weight coefficient between difference and practical pesticide-seeds ratio, can designed, designed coefficient according to demand；
S22: carrying out unified normalized to time-varying parameter, the time-varying parameter optimized and revised, and specific adjustment is public
Formula are as follows:Wherein,For original parameter value, xiFor parameter after normalization；PLiAnd PUiRespectively correspond under parameter
Boundary and the upper bound；Wherein, the time-varying parameter includes pesticide-seeds ratio, main motor frequency, batch duration, being delayed for medicine duration, pump supplies
Medicine, discharge duration, pump rated power and any parameter being coated in quality；
S23: it is inputted the time-varying parameter after step S23 normalized as neural network model, qualification rate will be coated
As output, the prediction output of neural network is set, and coating qualification rate here is the seed of the practical acquisition in step S21
Qualification rate, the prediction output of neural network are that the expectation in step S21 is coated qualification rate；The nerve net used in the present embodiment
Network model is BP neural network, and referring to Fig. 5, the output for hiding node layer isBy adding for input layer node to hidden layer node
Power is expressed as Wih；W is expressed as by the weighting of hidden layer node to output layer nodehj；Subscript i, h, j respectively indicate a certain input
Node hides node layer and output node, and subscript k indicates the serial number of training pair；
S24: when algorithm enters in some field, in order to further effectively improve parameter optimization, using artificial bee colony
Algorithm allows parameter to adjust toward excellent directional variance, while avoiding falling into local optimum again；
S25: by each circulation feedback as a result, being coated qualification rate, return step in conjunction with the obtained expectation of step S23
Evaluation function value is calculated in S21, selects adjustment parameter according to evaluation function value.Additionally due to there may be illegal for parameter adjustment
Solution, system will take evasion tactics, while can also be equipped with stipulated number for parameter variation, fall into extremely to limit parameter optimization
In circulation.
The carrying out practically process of expert control system of the invention are as follows:
After system starting, throwing disc motor, drum motor are opened, the feed inlet below feed bin is successively opened, is criticized until reaching
Secondary weight closes feed inlet, and feed bin is put into capsuled seed, setting is coated quality, qualification rate target value, and determines seed phase
New kind and characteristic can be added when the seed variety for not having to be coated in system by closing parameter；After setting, system is given
The coating of the coating parameter and prediction that optimize out is as a result, the parameter value of recommendation can be modified, while setting image is examined in systems
It surveys, be coated the relevant parameters such as operation, after determination, system enters automatic coating state, and by specified parameter operation, seed is being rolled
Loading pump is atomized after coating agent is sprayed onto throwing disc after bucket operation setting time, is coated and is completed after mixing setting time with seed,
It is discharged from discharge port, sampling a part to image detecting system, image detecting system Real-time Feedback is coated quality and qualification rate, ginseng
Result is written knowledge base and adjusts machined parameters in real time by number optimization modules by self study, optimization, into next batch plus
Work, the processing capacity until reaching setting terminate.
What has been described above is only a preferred embodiment of the present invention, it is noted that for those of ordinary skill in the art
For, without departing from the concept of the premise of the invention, various modifications and improvements can be made, these belong to the present invention
Protection scope.
Claims (8)
1. a kind of expert control system based on batch seed-coating machine, including seed-coating machine and image detecting system (3), the coating
Machine is batch seed-coating machine, is made of medicine system, charging system, coated systems and PLC control module (14), the PLC control
Molding block (14) is connect with medicine system, charging system and coated systems signal respectively, for controlling seed-coating machine operation；The figure
As detection system (3) are set to the side of coated systems, signal input part and PLC control module (14) of image detecting system (3)
Signal output end signal connection, for detect seed pelleting quality and Real-time Feedback coating qualification rate, it is characterised in that: also wrap
Expert system is included, expert's decorum is set to the side of image detecting system, including control cabinet (1) and display screen (2), described aobvious
Display screen (2) is installed on the front of control cabinet (1), is equipped with human-computer interaction interface (101), base module in the control cabinet (1)
(102), inference engine module (103), feedback self-learning module (104) and control centre, the control centre are industrial personal computer
(105), the industrial personal computer (105) is electrically bi-directionally connected human-computer interaction interface (101), feedback self-learning module (104) respectively
With the PLC control module (14) of seed-coating machine, the human-computer interaction interface (101) electrically output connection base module (102), institute
State feedback self-learning module (104) electrically output connection inference engine module (103), the letter of feedback self-learning module (104)
Number input terminal is also connect with the signal output end signal of image detecting system (3), for receiving the packet of image detecting system feedback
Clothing qualification rate.
2. a kind of expert control system based on batch seed-coating machine according to claim 1, it is characterised in that: described to add
Medicine system is set to the side of coated systems, including medicine storing drum (11), loading pump (10) and grug transportation tube (9)；The charging system is set
In the top of coated systems, including feeding chamber (7) and feed bin (8)；The coated systems include throwing disc (6), drum (5), discharging
Mouth (4), throwing disc motor (13) and drum motor (12)；One end of the grug transportation tube (9) is located in medicine storing drum (11), other end position
In the top of throwing disc (6), grug transportation tube (9) is equipped with loading pump (10), and grug transportation tube (9) pumps (10) for medicine storing drum by the loading
(11) coating agent for seed in is delivered to throwing disc (6)；The feeding chamber (7) is located at the top of drum (5), and feeding chamber (7) is just
Top is feed bin (8), and seed is put into drum (5) by feeding chamber (7) by the feed bin (8)；The throwing disc (6) is located at drum
(5) lower part of middle part position on the upper side in, throwing disc (6) is equipped with throwing disc motor (13), the throwing disc (6) and throwing disc motor (13) electricity
Connection drives its rotation by throwing disc motor (13) control；The lower section of throwing disc motor (13) is equipped with drum motor (12), the drum
(5) it is electrically connected with drum motor (12), its rotation is driven by drum motor (12) control；The discharge port (4) is located at drum (5)
Side wall, the end of discharge port (4) is equipped with image detecting system (3)；The signal output end of the PLC control module (14) is distinguished
It is connect with the signal input part of loading pump (10), throwing disc motor (13) and drum motor (12).
3. a kind of expert control system based on batch seed-coating machine according to claim 2, it is characterised in that: the material
Weighing sensor is equipped in storehouse (8), the signal input part of the weighing sensor and the signal of PLC control module (14) export
End connection, for controlling the charge weight of each batch.
4. a kind of expert control system based on batch seed-coating machine according to claim 2, it is characterised in that: described to get rid of
Disk (6) and drum (5) are the trapezoidal hollow round table in section.
5. a kind of control method of expert control system based on batch seed-coating machine according to claim 1, feature
It is, comprises the following specific steps that:
S1: expert system and image monitoring system start and initialize；
S2: expert system recommends to wrap according to coating quality target value set by user and seed characteristics, by neural network model
Each machined parameters of clothing machine, and confirmed or modified by user；
S3: seed-coating machine receives the parameter of user's confirmation or modification, is coated operation；
S4: the sampling period that image detecting system is arranged according to expert system is coated quality to product and qualification rate detects,
And Real-time Feedback optimizes to expert system for reasoning；
The further on-line training neural network model of result of S5: expert system receiving step S4 feedback, works as neural network model
Predicted value accuracy rate in stipulated number then starts the coating optimisation strategy based on artificial bee colony algorithm in reasonable error,
Otherwise return step S2 redefines each machined parameters of seed-coating machine, until actual processing result is in the reasonable field of expectation target
Then stop optimizing.
6. a kind of control method of expert control system based on batch seed-coating machine according to claim 5, feature
Be: in the step S2, each machined parameters of seed-coating machine be by expert system feedback self-learning module and inference engine module into
Row is fuzzy to be recommended, the specific steps are as follows:
S21: meet qualification rate for expectation target and reach requirement, design multiple target cost function, multiple target cost function is specific
Are as follows: min S=α | z1|+β|M|,z1=yd-yp1；Wherein, S is evaluation function；z1For expectation and practical qualification rate deviation；yp1For
The seed qualification rate actually obtained；ydQualification rate is coated for expectation；M is pesticide-seeds ratio；α and β be respectively be directed to qualification rate deviation and
Weight coefficient between practical pesticide-seeds ratio；
S22: carrying out unified normalized to time-varying parameter, and the time-varying parameter optimized and revised specifically adjusts formula are as follows:Wherein,For original parameter value, xiFor parameter after normalization；PLiAnd PUiRespectively correspond to the lower bound of parameter and upper
Boundary；
S23: it is inputted the time-varying parameter after step S23 normalized as neural network model, the seed that will actually obtain
As output, the prediction output that neural network is arranged is qualification rate；
S24: using artificial bee colony algorithm, allows parameter to adjust toward excellent directional variance, while avoiding falling into local optimum again；
S25: by each circulation feedback as a result, being coated qualification rate, return step S21 meter in conjunction with the obtained expectation of step S23
Calculation obtains evaluation function value, selects adjustment parameter according to evaluation function value.
7. a kind of control method of expert control system based on batch seed-coating machine according to claim 6, feature
Be: in the step S22, time-varying parameter includes pesticide-seeds ratio, main motor frequency, batch duration, being delayed for medicine duration, pump supplies
Medicine, discharge duration, pump rated power and any parameter being coated in quality.
8. a kind of control method of expert control system based on batch seed-coating machine according to claim 6, feature
Be: in the step S25, system takes evasion tactics, while stipulated number is arranged for parameter variation, limits parameter optimization
Fall into endless loop.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910698404.5A CN110501983B (en) | 2019-07-31 | 2019-07-31 | Expert control system and control method based on batch-type coating machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910698404.5A CN110501983B (en) | 2019-07-31 | 2019-07-31 | Expert control system and control method based on batch-type coating machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110501983A true CN110501983A (en) | 2019-11-26 |
| CN110501983B CN110501983B (en) | 2021-03-26 |
Family
ID=68587054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910698404.5A Active CN110501983B (en) | 2019-07-31 | 2019-07-31 | Expert control system and control method based on batch-type coating machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110501983B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113547162A (en) * | 2021-07-30 | 2021-10-26 | 武汉科技大学 | Circle shear parameter integrated control system and method |
| WO2022046062A1 (en) * | 2020-08-28 | 2022-03-03 | Siemens Corporation | Failure prediction in surface treatment processes using artificial intelligence |
Citations (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2324754Y (en) * | 1998-04-03 | 1999-06-23 | 王洪斌 | Spraying type seed dressing machine |
| CN2377808Y (en) * | 1999-07-23 | 2000-05-17 | 徐至仁 | Seed coating machine |
| US20020049521A1 (en) * | 1999-03-19 | 2002-04-25 | Ruffner Bryan John | Multifunctional mobile appliance |
| US6582516B1 (en) * | 1999-11-29 | 2003-06-24 | Gustafson, Llc | Continuous batch seed coating system |
| CN101689044A (en) * | 2007-04-12 | 2010-03-31 | 西门子公司 | Method for computer-supported control and/or regulation of a technical system |
| CN101782771A (en) * | 2010-03-17 | 2010-07-21 | 东华大学 | Spinning process intelligent optimized design method based on immune neural network |
| CN201569892U (en) * | 2009-09-22 | 2010-09-01 | 赵武云 | Automatic control device of seed coater based on singlechip |
| EP2409981A1 (en) * | 2003-07-02 | 2012-01-25 | Verenium Corporation | Glucanases, nucleic acids encoding them and methods for making and using them |
| CN102540879A (en) * | 2011-12-28 | 2012-07-04 | 北京工业大学 | Multi-target evaluation optimization method based on group decision making retrieval strategy |
| US20120258505A1 (en) * | 2008-08-29 | 2012-10-11 | Bunge Oils, Inc. | Hydrolases, nucleic acids encoding them and methods for making and using them |
| CN103444307A (en) * | 2012-05-28 | 2013-12-18 | 甘肃农业大学 | Electronic control system based on expert system of intelligent seed coating machine |
| CN103808509A (en) * | 2014-02-19 | 2014-05-21 | 华北电力大学（保定） | Fan gear box fault diagnosis method based on artificial intelligence algorithm |
| CN103843493A (en) * | 2013-12-03 | 2014-06-11 | 石河子市华农种子机械制造有限公司 | Large numerical control seed coating system |
| CN104299052A (en) * | 2014-10-12 | 2015-01-21 | 刘岩 | Building energy consumption prediction method based on artificial bee colony algorithm and neural network |
| CN104763999A (en) * | 2015-03-04 | 2015-07-08 | 内蒙古瑞特优化科技股份有限公司 | Power plant pulverized coal boiler combustion performance online optimizing method and system |
| CN104855002A (en) * | 2015-06-09 | 2015-08-26 | 湖南力本种业科技有限公司 | Batch continuous coating control method and batch continuous coating machine with seed coating premixing function |
| WO2015179005A1 (en) * | 2014-05-20 | 2015-11-26 | Usc, L.L.C. | Batch seed coating apparatus |
| WO2016025334A1 (en) * | 2014-08-10 | 2016-02-18 | Carnegie Institution Of Washington | Photosynthetic acclimation and increased biomass production in fluctuating light environments |
| CN205596545U (en) * | 2016-04-26 | 2016-09-28 | 农业部南京农业机械化研究所 | Mechanism is broken up to peanut capsule blanking |
| CN106529672A (en) * | 2016-11-09 | 2017-03-22 | 上海电机学院 | Selective neural network integration algorithm based on artificial bee colony algorithm |
| WO2017084560A1 (en) * | 2015-11-16 | 2017-05-26 | Novozymes A/S | Cellulase variants and polynucleotides encoding same |
| US20170223986A1 (en) * | 2011-11-25 | 2017-08-10 | Novozymes A/S | Polypeptides Having Lysozyme Activity and Polynucleotides Encoding Same |
| CN107154042A (en) * | 2017-05-18 | 2017-09-12 | 湖南大学 | A kind of seed-coating machine visible detection method and device |
| CN107321276A (en) * | 2017-06-16 | 2017-11-07 | 天津科技大学 | A kind of controllable heat fusing fluid bed microcapsules preparation system of product quality and preparation method |
| CN107506565A (en) * | 2017-10-16 | 2017-12-22 | 安徽工业大学 | Method for building up based on neutral net alloy cast steel roll Expert System for Materials Design |
| CN108244105A (en) * | 2018-01-17 | 2018-07-06 | 安徽省华禾种业有限公司 | A kind of vegetable seeds coating agent and preparation method thereof |
| CN108464032A (en) * | 2015-10-16 | 2018-08-28 | 罗马大学 | The routing policy of node in underwater network and the method for re-transmission policy and its realization device are managed in a manner of adaptive and engagement |
| CN108491968A (en) * | 2018-03-17 | 2018-09-04 | 北京工业大学 | Based on agricultural product quality and safety emergency resources scheduling model computational methods |
| CN108593663A (en) * | 2018-06-11 | 2018-09-28 | 农业部南京农业机械化研究所 | A kind of seed pelleting qualification rate detecting system and method |
| CN108614415A (en) * | 2018-03-27 | 2018-10-02 | 苏州联点数据技术有限公司 | A kind of intelligence control system and control method of plant growth factor |
| US10225974B2 (en) * | 2016-08-10 | 2019-03-12 | Usc, Llc | Batch seed coater with lift assembly |
| CN109634098A (en) * | 2018-12-25 | 2019-04-16 | 江苏大学 | A kind of fattening house environment conditioning system and method |
| CN109781099A (en) * | 2019-03-08 | 2019-05-21 | 兰州交通大学 | A kind of navigation methods and systems of adaptive UKF algorithm |
| CN209085657U (en) * | 2017-08-02 | 2019-07-09 | 强力物联网投资组合2016有限公司 | For data gathering system related or industrial environment with chemical production technology |
-
2019
- 2019-07-31 CN CN201910698404.5A patent/CN110501983B/en active Active
Patent Citations (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2324754Y (en) * | 1998-04-03 | 1999-06-23 | 王洪斌 | Spraying type seed dressing machine |
| US20020049521A1 (en) * | 1999-03-19 | 2002-04-25 | Ruffner Bryan John | Multifunctional mobile appliance |
| CN2377808Y (en) * | 1999-07-23 | 2000-05-17 | 徐至仁 | Seed coating machine |
| US6582516B1 (en) * | 1999-11-29 | 2003-06-24 | Gustafson, Llc | Continuous batch seed coating system |
| EP2409981A1 (en) * | 2003-07-02 | 2012-01-25 | Verenium Corporation | Glucanases, nucleic acids encoding them and methods for making and using them |
| CN101689044A (en) * | 2007-04-12 | 2010-03-31 | 西门子公司 | Method for computer-supported control and/or regulation of a technical system |
| US20120258505A1 (en) * | 2008-08-29 | 2012-10-11 | Bunge Oils, Inc. | Hydrolases, nucleic acids encoding them and methods for making and using them |
| CN201569892U (en) * | 2009-09-22 | 2010-09-01 | 赵武云 | Automatic control device of seed coater based on singlechip |
| CN101782771B (en) * | 2010-03-17 | 2011-12-14 | 东华大学 | Spinning process intelligent optimized design method based on immune neural network |
| CN101782771A (en) * | 2010-03-17 | 2010-07-21 | 东华大学 | Spinning process intelligent optimized design method based on immune neural network |
| US20170223986A1 (en) * | 2011-11-25 | 2017-08-10 | Novozymes A/S | Polypeptides Having Lysozyme Activity and Polynucleotides Encoding Same |
| CN102540879A (en) * | 2011-12-28 | 2012-07-04 | 北京工业大学 | Multi-target evaluation optimization method based on group decision making retrieval strategy |
| CN103444307A (en) * | 2012-05-28 | 2013-12-18 | 甘肃农业大学 | Electronic control system based on expert system of intelligent seed coating machine |
| CN103843493A (en) * | 2013-12-03 | 2014-06-11 | 石河子市华农种子机械制造有限公司 | Large numerical control seed coating system |
| CN103843493B (en) * | 2013-12-03 | 2016-04-20 | 石河子市华农种子机械制造有限公司 | Large-sized numerical control seed pelleting system |
| CN103808509A (en) * | 2014-02-19 | 2014-05-21 | 华北电力大学（保定） | Fan gear box fault diagnosis method based on artificial intelligence algorithm |
| WO2015179005A1 (en) * | 2014-05-20 | 2015-11-26 | Usc, L.L.C. | Batch seed coating apparatus |
| WO2016025334A1 (en) * | 2014-08-10 | 2016-02-18 | Carnegie Institution Of Washington | Photosynthetic acclimation and increased biomass production in fluctuating light environments |
| CN104299052A (en) * | 2014-10-12 | 2015-01-21 | 刘岩 | Building energy consumption prediction method based on artificial bee colony algorithm and neural network |
| CN104763999A (en) * | 2015-03-04 | 2015-07-08 | 内蒙古瑞特优化科技股份有限公司 | Power plant pulverized coal boiler combustion performance online optimizing method and system |
| CN104855002B (en) * | 2015-06-09 | 2017-10-13 | 湖南力本农业装备股份有限公司 | The batch continous way for possessing seed coat agent pre-mixing function is coated control method and seed-coating machine |
| CN104855002A (en) * | 2015-06-09 | 2015-08-26 | 湖南力本种业科技有限公司 | Batch continuous coating control method and batch continuous coating machine with seed coating premixing function |
| CN108464032A (en) * | 2015-10-16 | 2018-08-28 | 罗马大学 | The routing policy of node in underwater network and the method for re-transmission policy and its realization device are managed in a manner of adaptive and engagement |
| WO2017084560A1 (en) * | 2015-11-16 | 2017-05-26 | Novozymes A/S | Cellulase variants and polynucleotides encoding same |
| CN205596545U (en) * | 2016-04-26 | 2016-09-28 | 农业部南京农业机械化研究所 | Mechanism is broken up to peanut capsule blanking |
| US10225974B2 (en) * | 2016-08-10 | 2019-03-12 | Usc, Llc | Batch seed coater with lift assembly |
| CN106529672A (en) * | 2016-11-09 | 2017-03-22 | 上海电机学院 | Selective neural network integration algorithm based on artificial bee colony algorithm |
| CN107154042A (en) * | 2017-05-18 | 2017-09-12 | 湖南大学 | A kind of seed-coating machine visible detection method and device |
| CN107321276A (en) * | 2017-06-16 | 2017-11-07 | 天津科技大学 | A kind of controllable heat fusing fluid bed microcapsules preparation system of product quality and preparation method |
| CN209085657U (en) * | 2017-08-02 | 2019-07-09 | 强力物联网投资组合2016有限公司 | For data gathering system related or industrial environment with chemical production technology |
| CN107506565A (en) * | 2017-10-16 | 2017-12-22 | 安徽工业大学 | Method for building up based on neutral net alloy cast steel roll Expert System for Materials Design |
| CN108244105A (en) * | 2018-01-17 | 2018-07-06 | 安徽省华禾种业有限公司 | A kind of vegetable seeds coating agent and preparation method thereof |
| CN108491968A (en) * | 2018-03-17 | 2018-09-04 | 北京工业大学 | Based on agricultural product quality and safety emergency resources scheduling model computational methods |
| CN108614415A (en) * | 2018-03-27 | 2018-10-02 | 苏州联点数据技术有限公司 | A kind of intelligence control system and control method of plant growth factor |
| CN108593663A (en) * | 2018-06-11 | 2018-09-28 | 农业部南京农业机械化研究所 | A kind of seed pelleting qualification rate detecting system and method |
| CN109634098A (en) * | 2018-12-25 | 2019-04-16 | 江苏大学 | A kind of fattening house environment conditioning system and method |
| CN109781099A (en) * | 2019-03-08 | 2019-05-21 | 兰州交通大学 | A kind of navigation methods and systems of adaptive UKF algorithm |
Non-Patent Citations (4)
| Title |
|---|
| VASQUCZ RUBCN PURROY: "" Expert system based on a fuzzy logic model for the analysis of the sustainable livestock production dynamic system"", 《COMPUTERS AND ELECTRONICS IN AGRICULTURE》 * |
| 杨婉霞: ""基于专家***的智能化种子包衣机控制***研制"", 《中国农机化学报》 * |
| 胡良龙: ""基于PLC的种子包衣机自动控制***设计与实现"", 《农业工程学报》 * |
| 韩柏和: ""国内外种子丸粒化包衣设备发展现状及存在问题"", 《中国农机化学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022046062A1 (en) * | 2020-08-28 | 2022-03-03 | Siemens Corporation | Failure prediction in surface treatment processes using artificial intelligence |
| CN113547162A (en) * | 2021-07-30 | 2021-10-26 | 武汉科技大学 | Circle shear parameter integrated control system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110501983B (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110501983A (en) | Expert control system and control method based on batch seed-coating machine | |
| CN109937856B (en) | Household automatic irrigation system for herbaceous and woody plants and working method thereof | |
| CN104460582B (en) | A kind of Internet of Things intelligent irrigation fertilising control method and system based on fuzzy control | |
| CN102645927B (en) | Monitoring system for aquaculture environment of fresh-water fish on basis of wireless sensor network | |
| CN107183227A (en) | A kind of intelligent tea production line | |
| CN108224446B (en) | A kind of automatic combustion real-time optimization decision-making technique of Refuse Incineration Process | |
| CN112327960B (en) | Intelligent control system for loosening and dampening equipment | |
| CN106434233B (en) | Intelligent control system and control method for white spirit production | |
| CN106192308A (en) | A kind of washing machine Intelligent feeding device and system | |
| CN106773721A (en) | A kind of aquaculture intelligence feeding system and its control method based on fuzzy control | |
| CN106383536A (en) | Greenhouse smart control system and method | |
| CN109543916A (en) | Silicon rod growth rate prediction model in a kind of polycrystalline silicon reducing furnace | |
| CN106718693A (en) | A kind of irrigation district Water Resource Adjustment And Control system and regulation and control method | |
| CN108425405A (en) | A kind of monitoring of networking water source and water supply by stage device and its monitoring system | |
| CN110567232A (en) | Large-scale automatic cooling chemical industry equipment of production industrial chemicals | |
| CN206189118U (en) | Washing machine intelligence feeding device and system | |
| CN106371485A (en) | Intelligent aquaculture system and method based on LABVIEW remote monitoring and control technology | |
| CN206713809U (en) | A kind of intelligent positive-pressure wind spraying aid type variable ratio frequency changer speed governing, which is thrown, to be waited for an opportunity | |
| CN115661547A (en) | Plant irrigation and maintenance method and system based on knowledge graph | |
| CN106719115A (en) | Intelligent fish feeding method and device | |
| CN110619409A (en) | Universal energy station scheduling method and device for self-adaptive perturbation quantum particle swarm | |
| CN108175121A (en) | Self-correction method/system, computer readable storage medium and the equipment of parameter | |
| CN111242903A (en) | Automatic counting platform and method for pigling | |
| CN113885310B (en) | Intelligent control system for vacuum dry pump test | |
| CN113692833A (en) | Water pump irrigation system and method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |