CN103984229B - A kind of neural network control method of lifting mechanism of tower crane governing system - Google Patents
A kind of neural network control method of lifting mechanism of tower crane governing system Download PDFInfo
- Publication number
- CN103984229B CN103984229B CN201410183786.5A CN201410183786A CN103984229B CN 103984229 B CN103984229 B CN 103984229B CN 201410183786 A CN201410183786 A CN 201410183786A CN 103984229 B CN103984229 B CN 103984229B
- Authority
- CN
- China
- Prior art keywords
- neural network
- crane
- output
- input
- layer
- 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.)
- Active
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 30
- 230000007246 mechanism Effects 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 16
- 210000002569 neuron Anatomy 0.000 claims abstract description 13
- 238000003062 neural network model Methods 0.000 claims abstract description 3
- 239000000725 suspension Substances 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 7
- 230000007935 neutral effect Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000000630 rising effect Effects 0.000 claims 1
- 230000001537 neural effect Effects 0.000 abstract description 2
- 230000000505 pernicious effect Effects 0.000 abstract description 2
- 238000012546 transfer Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Landscapes
- Control And Safety Of Cranes (AREA)
- Feedback Control In General (AREA)
Abstract
The present invention relates to crane hoisting mechanism control field,More particularly to the neural network control method of lifting mechanism of tower crane governing system that a kind of utilization neural net method is controlled to the governing system in lifting mechanism of tower crane,Using ANN Control principle,Set up the topological structure of BP neural network Controlling model,Then BP neural network is trained,Determine hidden neuron number,The threshold value of connection weight and neuron between each layer neuron,Try to achieve BP neural network Controlling model,Input variable sampled data in crane each cycle is input to the BP neural network model that obtains of training and output signal f ' can be tried to achieve,BP neural network has generalization ability in the present invention,Control accuracy can be improved,Realize that Lift Mechanism in Power Hoist steadily accelerates and slows down,It is prevented effectively from the pernicious impact of mechanical transfer,Reach raising operating efficiency,The extension tower crane life-span,Ensure the purpose of the safety and reliability of tower crane.
Description
Technical field
Neural net method is utilized to tower the present invention relates to crane hoisting mechanism control field, more particularly to one kind
The ANN Control side of the lifting mechanism of tower crane governing system that the governing system in heavy-duty machine lifting mechanism is controlled
Method.
Background technology
In the lifting mechanism of derrick crane, the control of governing system is most important.Traditional governor system control side
Formula, speed control with eddy current braking, rotor series resistance speed, change number of pole-pairs speed governing etc., take step speed regulation, speed adjustable range
It is small；Low speed poor performance in place, low level operation easily causes resistor, eddy-current brake to generate heat；Starting current is big, and power network is impacted
Greatly；Often the mechanical braking in high speed is run, makes brake block easily be worn；Power factor is low, makes line loss big.
Fuzzy control method using microcomputer control, by the rotating speed and the lifting velocity of suspension hook of frequency converter regulation motor.Choosing
Select 2 input variables that lifting altitude h and load weight g is fuzzy controller.Lifting altitude h is divided into 7 grades, its opinion
Domain H={ -3, -2, -1,0,1,2,3 }, grade 0 is set as the 1/2 of object height, is down negative direction, up for just
Direction.Take 7 Linguistic Values:W1 (negative big), W2 (in negative), W3 (negative small), W4 (zero), W5 (just small), W6 (center),
W7 (honest), is designated as: NB、NM、NS、Z、PS、PM、PB.Similarly, lift heavy is also divided into 7 grades, its domain be G=-3, -
2, -1,0,1,2,3 }, it is set as grade 0 the 1/2 of the biggest lifting capacity of tower crane, it is bigger than this value for just, than this
It is negative that value is small.It is G1 (negative big), G2 (in negative), G3 (negative small), G4 (zero), G5 (just small), G6 to take 7 Linguistic Values
(center), G7 (honest), is designated as: NB、NM、NS、Z、PS、PM、PB.Control of the actuator to the velocity of rotation of motor is to pass through
The supply frequency realization of motor is adjusted, because the rotating speed formula of AC asynchronous motor:N=60f (1-s)/p, wherein,
N is the rotating speed (rev/min) of AC motor rotor, and p is the number of pole-pairs of motor stator winding, and f is motor stator frequency of supply
(HZ), s is revolutional slip.Changing frequency can change rotating speed, the rate of change f' of the output control amount selected frequency of fuzzy controller,
To realize controls in advance.F' is also divided into 7 grades, and it is negative just, to slow down to accelerate, its domain be F=-3, -2, -1,0,1,2,
3}.Take 7 Linguistic Values:F1 (negative big), F2 (in negative), F3 (negative small), F4 (zero), F5 (just small), F6 (center), F7
(honest), is designated as: NB、NM、NS、Z、PS、PM、PB.
Fuzzy rule can obtain according to safety operation experience as shown in table 1.Using the fuzzy control in MATLAB tool boxes
System, can try to achieve fuzzy controller input signal and output control signal corresponding table（Referred to as fuzzy control responds table）Such as table 2.
On the basis of off-line calculation, the control signal f ' inquiry tables shown such as table 3 are set up, it is stored in calculator memory
In, and work out a corresponding subprogram tabled look-up.In actual control process, fuzzy controller need to only carry out following work:
(1) in each controlling cycle, using weight sensor and height sensor sampling load weight and suspension hook rise
Rise；
(2) the lifting altitude obfuscation of the weight and suspension hook of load, calculates discrete point of gear value；
(3) according to the discrete point of corresponding row and column of gear value look-up table 3, output control amount f ' can be drawn.
Fuzzy control method is used for Lift Mechanism in Power Hoist suspension hook speed control, can be prevented effectively from the machine occurred in tower crane work
Tool impacts and rush of current, reduces the generation of abrasion and the contingency of brake shoe, is extended the tower crane life-span, makes the peace of tower crane
Full property and reliability are improved.But fuzzy controller each controlling cycle must act the load weight and suspension hook sampled
Rise carries out Fuzzy processing, calculates discrete point of gear value, can according to the discrete point of corresponding row and column of gear value look-up table 3,
Output control amount f ' is tried to achieve, operation time had so not only been increased but also had been influenceed control accuracy.
The content of the invention
It is an object of the invention to overcome the shortcomings of existing lifting mechanism of tower crane governor system control technology, and carry
For a kind of neural network control method of lifting mechanism of tower crane governing system.
The technical solution adopted in the present invention：
The step of a kind of neural network control method of lifting mechanism of tower crane governing system, the method, is as follows：
Step 1）, using crane load weight g and suspension hook lifting altitude h as neutral net two input variables, rise
The rate of change f ' of heavy-duty machine motor stator frequency of supply f is controlled quentity controlled variable as the output variable of neutral net；If crane load weight
The domain for measuring g is G, and load weight is divided into 7 grades, is represented with -3, -2, -1,0,1,2,3,
That is G={ -3, -2, -1,0,1,2,3 }, sets 1/2 corresponding grade 0 of the maximum load weight of crane,
Than this value weight for just, lighter than this value is negative, 7 fuzzy language values are taken for G1, G2, G3, G4, G5, G6, G7
, it is designated as:NB, NM, NS, Z, PS, PM, PB, wherein, G1 represents negative big, and during G2 represents negative, G3 represents negative small, and G4 represents zero, G5
Represent just small, G6 represents center, and G7 represents honest；
If the domain of the suspension hook lifting altitude h of crane is W, and lifting altitude is divided into 7 grades, with -3, -2, -
1,0,1,2,3 represents,
That is W={ -3, -2, -1,0,1,2,3 }, sets 1/2 corresponding grade 0 of the maximum lifting height of crane,
Than this value weight for just, lighter than this value is negative, 7 fuzzy language values are taken for W1, W2, W3, W4, W5, W6, W7
, it is designated as:NB, NM, NS, Z, PS, PM, PB, wherein, W1 represents negative big, and during W2 represents negative, W3 represents negative small, and W4 represents zero, W5
Represent just small, W6 represents center, and W7 represents honest；
If the domain of controlled quentity controlled variable f ' is F, and controlled quentity controlled variable is divided into 7 grades, with -3, -2, -1,0,1,2,3 tables
Show,
That is F={ -3, -2, -1,0,1,2,3 }, sets 1/2 corresponding grade 0 of the maximum controlled quentity controlled variable of crane, than
This value weight for just, lighter than this value is negative, take 7 fuzzy language values be F1, F2, F3, F4, F5, F6, F7,
It is designated as:NB, NM, NS, Z, PS, PM, PB, wherein, F1 represents negative big, and during F2 represents negative, F3 represents negative small, and F4 represents zero, F5 tables
Show just small, F6 represents center, F7 represents honest；Fuzzy reasoning table can be obtained according to safety operation experience；Using MATLAB tool boxes
In Fuzzy control system, fuzzy controller input signal and output control signal corresponding table can be tried to achieve；
Step 2）, to step 1）In table 2 in input signal crane load weight and suspension hook lifting altitude and defeated
Go out control signal and do normalized；
Step 3）, set up the topological structure of BP neural network Controlling model:Crane load weight g and suspension hook lifting altitude
H is two input variables of input layer；The rate of change of frequency is the output variable that controlled quentity controlled variable f ' is output layer；
Step 4）, training BP neural network, determine the connection weight between hidden neuron number, each layer neuron and god
Through the threshold value of unit, BP neural network Controlling model is tried to achieve；
Step 5）, crane each controlling cycle in, using the Neural Network Toolbox in MATLAB, only will need to sample
Crane load weight g and the suspension hook lifting altitude h input BP neural network Controlling models that obtain of training, you can try to achieve output
Controlled quentity controlled variable f '.
Described BP neural network model is with containing one layer of the three of hidden layer layers of feed-forward type network structure, by load weight g
With suspension hook lifting altitude h as two input variables of input layer；The rate of change of frequency is one that controlled quentity controlled variable f ' is output layer defeated
Go out variable, hidden layer has 10 neurons；The transmission function of hidden layer and output layer selects function, due to activation primitive
Using, therefore need formula to being input into and exporting initial dataDo and return
One change is processed, and makes its value between [0.1,0.9].
Described BP network trainings mode includes two stages：Feed-forward strategy and back-propagation phase.Feed-forward strategy refers to
Input vector is input into by input layer, output layer is reached with feed-forward mode via hidden layer, and obtain the output of network；Backpropagation rank
Section refers to subtract network output valve by desired output, obtains error signal, and this error signal is reversely successively then passed back into net
In network, and then change connection weight and threshold value.
The beneficial effects of the present invention are:The present invention provides a kind of BP god of governing system in lifting mechanism of tower crane
Through network Controlling model, because BP neural network has generalization ability, crane load weight and suspension hook for sampling rise
The actual numerical value of rise directly inputs BP neural network Controlling model, you can try to achieve output control amount f '.Overcome Fuzzy Control
The crane load weight of sampling and suspension hook lifting altitude must be carried out Fuzzy processing by device processed each controlling cycle, be calculated
Go out discrete point of gear value, the technological deficiency of controlled quentity controlled variable f ' can be found, so as to control accuracy can be improved, realize Lift Mechanism in Power Hoist
It is steady to accelerate and slow down, the pernicious impact of mechanical transfer is prevented effectively from, reach raising operating efficiency, extension tower crane life-span, ensure
The purpose of the safety and reliability of tower crane.
Brief description of the drawings
Fig. 1 is the topology of the BP neural network Controlling model of the governing system in lifting mechanism of tower crane of the present invention
Structure chart.
Fig. 2 is that error just reaches 1e-3 after application training sample of the present invention is trained 13 times to BP neural network.
Specific embodiment
（1）Set up BP neural network structural topologies
As shown in figure 1, using with containing one layer of the three of hidden layer layers of feed-forward type network structure, by crane load weight g and
Suspension hook lifting altitude g is used as two input variables of input layer；The rate of change of frequency is the output that controlled quentity controlled variable f ' is output layer
Variable, hidden layer has 10 neurons；The transmission function of hidden layer and output layer selects function 。
（2）The standardization of sample data
Because activation primitive is used, therefore need to do normalized, formula to being input into and exporting initial data, make its value between [0.1,0.9].
（3）Training BP neural network
BP network trainings mode includes two stages：Feed-forward strategy and back-propagation phase.Feed-forward strategy refers to by being input into
Layer input input vector, reaches output layer, and obtain the output of network via hidden layer with feed-forward mode；Back-propagation phase refers to
Subtract network output valve by desired output, obtain error signal, be then reversely successively passed back in network this error signal, enter
And change connection weight and threshold value.
If Xk is input vector,,It is the number of sample,It isInput layer and hidden layer during secondary iterationBetween weight vector,It isHidden layer during secondary iterationWith hidden layerBetween weight vector,It isSecondary iteration is hidden layerWith
Weight vector between output layer,,It isNet during secondary iteration
The reality output of network,It is desired output.
BP algorithm step is as follows:
(I) initialize:Assign less random nonzero value in ;
(II) input sampleAnd desired output 。n=0;
(III) to input sample, the input signal of forward calculation BP every layer of neuron of networkAnd output signal 。
(IV) by desired outputThe reality output tried to achieve with previous stepCalculation error, whether judge it
Meet and require, if satisfaction goes to (VIII)；It is unsatisfactory for going to (V).
(V) judgeWhether maximum iteration is more than, if more than (VIII) is gone to, otherwise, to input sample, instead
To every layer of partial gradient of neuron of calculating.Wherein,
(VI) it is calculated as follows modified weight, and weights are corrected,It is learning rate., go to (III).
(VIII) judge whether to finish all of training sample, be to terminate, otherwise return to (II).
With the data in fuzzy control response table as training sample, training function selects trainlm, and step-up error is limited to
1e-3, limited number of time training is carried out to BP neural network.As shown in Fig. 2 after BP neural network training carries out 36 times, standard figures is missed
Difference just reaches 1e-3.
（4) weights and threshold value and calculated example of the BP neural network that training is obtained
The weights and threshold value of network：
IW =
-4.4030 2.3402
-0.6513 -5.9726
1.9988 2.6401
2.7534 5.6661
1.0848 2.7830
LW =
0.5612 1.7353 3.1821 -1.5932 -2.5713
b1 =
2.3266
4.5587
-2.7843
-4.6057
-0.3762
b2 =
1.6861
By returning inspection experiment, the value of the f ' in contrast network output quantity and fuzzy control response table finds BP network right and wrong
It is often effective.
The network has very strong generalization ability, to arbitrary load weight and suspension hook lifting altitude, can calculate output control
Variable f '.For example：
When input quantity is（- 2, -2.5）When, the corresponding output F=sim of BP neural network (net, (- 2, -2.5) ')=
0.8971, by obtaining tractive force F=3.971, contrast fuzzy control response table, it is known that this result is can after inverse normalization reduction
Capable.
Claims (1)
1. a kind of neural network control method of lifting mechanism of tower crane governing system, it is characterised in that：The step of the method
It is rapid as follows：
Step 1）, using crane load weight g and suspension hook lifting altitude h as neutral net two input variables, crane
The rate of change f ' of motor stator frequency of supply f is controlled quentity controlled variable as the output variable of neutral net；If crane load weight g's
Domain is G, and load weight is divided into 7 grades, is represented with -3, -2, -1,0,1,2,3,
That is G={ -3, -2, -1,0,1,2,3 }, sets 1/2 corresponding grade 0 of the maximum load weight of crane, than this
Individual value weight for just, lighter than this value is negative, take 7 fuzzy language values for G1, G2, G3, G4, G5, G6, G7, remember
For:NB, NM, NS, Z, PS, PM, PB, wherein, G1 represents negative big, and during G2 represents negative, G3 represents negative small, and G4 represents that zero, G5 is represented
Just small, G6 represents center, and G7 represents honest；
If the domain of the suspension hook lifting altitude h of crane is W, and lifting altitude is divided into 7 grades, with -3, -2, -1,0,
1,2,3 represents,
That is W={ -3, -2, -1,0,1,2,3 }, sets 1/2 corresponding grade 0 of the maximum lifting height of crane hook,
Than this value weight for just, lighter than this value is negative, 7 fuzzy language values are taken for W1, W2, W3, W4, W5, W6, W7
, it is designated as:NB, NM, NS, Z, PS, PM, PB, wherein, W1 represents negative big, and during W2 represents negative, W3 represents negative small, and W4 represents zero, W5
Represent just small, W6 represents center, and W7 represents honest；
If the domain of controlled quentity controlled variable f ' is F, and controlled quentity controlled variable is divided into 7 grades, represented with -3, -2, -1,0,1,2,3,
That is F={ -3, -2, -1,0,1,2,3 }, sets 1/2 corresponding grade 0 of the maximum controlled quentity controlled variable of crane, than this
Value weight for just, lighter than this value is negative, take 7 fuzzy language values for F1, F2, F3, F4, F5, F6, F7, remember
For:NB, NM, NS, Z, PS, PM, PB, wherein, F1 represents negative big, and during F2 represents negative, F3 represents negative small, and F4 represents that zero, F5 is represented
Just small, F6 represents center, and F7 represents honest；Fuzzy reasoning table can be obtained according to safety operation experience；Using in MATLAB tool boxes
Fuzzy control system, fuzzy controller input signal and output control signal corresponding table can be tried to achieve；
Step 2）, to step 1）In table 2 in input signal crane load weight and suspension hook lifting altitude and output control
Signal processed does normalized；
Step 3）, set up the topological structure of BP neural network Controlling model:Crane load weight g and suspension hook lifting altitude h are
Two input variables of input layer；The rate of change of frequency is the output variable that controlled quentity controlled variable f ' is output layer；
Step 4）, training BP neural network, determine the connection weight and neuron between hidden neuron number, each layer neuron
Threshold value, try to achieve BP neural network Controlling model；
Step 5）, crane each controlling cycle in, using the Neural Network Toolbox in MATLAB, only need to be by rising for sampling
The BP neural network Controlling model that heavy-duty machine load weight g and suspension hook lifting altitude h input training is obtained, you can try to achieve output control
Amount f '；
Described BP neural network model is with containing one layer of the three of hidden layer layers of feed-forward type network structure, by load weight g and to hang
Rise h is hooked as two input variables of input layer；The rate of change of frequency is that the output that controlled quentity controlled variable f ' is output layer becomes
Amount, hidden layer has 10 neurons；The transmission function of hidden layer and output layer selects function, because activation primitive is used, therefore need formula to being input into and exporting initial dataNormalize
Treatment, makes its value between [0.1,0.9]；
Described BP network trainings mode includes two stages：Feed-forward strategy and back-propagation phase, feed-forward strategy refer to by defeated
Enter layer input input vector, output layer is reached with feed-forward mode via hidden layer, and obtain the output of network；Back-propagation phase is
Finger subtracts network output valve by desired output, obtains error signal, is then reversely successively passed back in network this error signal,
And then change connection weight and threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410183786.5A CN103984229B (en) | 2014-05-04 | 2014-05-04 | A kind of neural network control method of lifting mechanism of tower crane governing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410183786.5A CN103984229B (en) | 2014-05-04 | 2014-05-04 | A kind of neural network control method of lifting mechanism of tower crane governing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103984229A CN103984229A (en) | 2014-08-13 |
| CN103984229B true CN103984229B (en) | 2017-06-06 |
Family
ID=51276248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410183786.5A Active CN103984229B (en) | 2014-05-04 | 2014-05-04 | A kind of neural network control method of lifting mechanism of tower crane governing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103984229B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106966296A (en) * | 2017-05-24 | 2017-07-21 | 安徽科恩新能源有限公司 | tower crane monitoring system based on fuzzy controller |
| CN110406539A (en) * | 2019-07-22 | 2019-11-05 | 杭州鸿泉物联网技术股份有限公司 | A kind of method and device identifying vehicle load state |
| CN110989361B (en) * | 2019-12-25 | 2022-04-12 | 武汉科技大学 | Grouping fuzzy control method based on weight online optimization |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544389A (en) * | 2013-10-18 | 2014-01-29 | 丽水学院 | Fault tree and fuzzy neural network based automobile crane fault diagnosis method |
| CN203497948U (en) * | 2013-10-18 | 2014-03-26 | 丽水学院 | Fuzzy neural network fault diagnosis device of auto crane |
| CN103701396A (en) * | 2013-12-13 | 2014-04-02 | 天津大学 | Motor rotating-speed tracking control method based on self-adaptive fuzzy neural network |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005538886A (en) * | 2002-09-13 | 2005-12-22 | ヤマハ発動機株式会社 | Fuzzy controller using a reduced number of sensors |
| CN101441441B (en) * | 2007-11-21 | 2010-06-30 | 新乡市起重机厂有限公司 | Design method of intelligent swing-proof control system of crane |
-
2014
- 2014-05-04 CN CN201410183786.5A patent/CN103984229B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544389A (en) * | 2013-10-18 | 2014-01-29 | 丽水学院 | Fault tree and fuzzy neural network based automobile crane fault diagnosis method |
| CN203497948U (en) * | 2013-10-18 | 2014-03-26 | 丽水学院 | Fuzzy neural network fault diagnosis device of auto crane |
| CN103701396A (en) * | 2013-12-13 | 2014-04-02 | 天津大学 | Motor rotating-speed tracking control method based on self-adaptive fuzzy neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103984229A (en) | 2014-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103984229B (en) | A kind of neural network control method of lifting mechanism of tower crane governing system | |
| Hafeez et al. | Self-tuned NFC and adaptive torque hysteresis-based DTC scheme for IM drive | |
| Yin et al. | Output power control for hydro-viscous transmission based continuously variable speed wind turbine | |
| JP5562366B2 (en) | Hybrid intelligent power control system and method | |
| CN108393892A (en) | A kind of robot feedforward torque compensation method | |
| CN107515598A (en) | Fired power generating unit distributed and coordinated control system based on multi-parameter dynamic matrix control | |
| CN103303800A (en) | Rotating control method of crane, rotating control system and crane | |
| CN105048896B (en) | A kind of brshless DC motor Direct Torque adaptive fuzzy control method | |
| JP2533683B2 (en) | Control device for hydraulic elevator | |
| Wang et al. | Antirollback control for gearless elevator traction machines adopting offset-free model predictive control strategy | |
| CN110589684A (en) | Anti-swing driving control method for crane | |
| Lovrec et al. | Dynamic behaviour of different hydraulic drive concepts–comparison and limits | |
| CN103696453B (en) | Control method and system used for excavator electric control pump | |
| CN103079978B (en) | Control device for elevator | |
| CN108396451A (en) | A kind of discrete velocity control method of Intelligent glove machine cylinder needle selection | |
| Kassem | Neural control design for isolated wind generation system based on SVC and nonlinear autoregressive moving average approach | |
| CN106655962B (en) | Electric vehicle Induction Motor-Driven system control method based on extreme learning machine | |
| CN110138293A (en) | A kind of BP neural network optimization chaotic control method based on double-fed wind power system | |
| Yang et al. | Loss‐minimization control of vector‐controlled induction motor drives | |
| CN104085792B (en) | Lifting machine frequency transformer and output frequency setting method thereof | |
| CN112987576B (en) | Neural network self-adaptive control method of non-contact suspension grabbing system | |
| CN108267970B (en) | Time-lag rotor active balance control system and method based on Smith model and single neuron PID | |
| JP6211214B2 (en) | Elevator control device | |
| Sit et al. | An efficient speed control method based on neuro-fuzzy modeling for asynchronous motors | |
| JP6578746B2 (en) | Hydroelectric power generation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xu Zhonghua Inventor before: Yu Jianli Inventor before: Xu Guangshan |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20170421 Address after: Yongchun County of Quanzhou City, Fujian province 362614 Gui Yang Zhen Wen Tai Cun No. 139 Applicant after: Yongchun Guiyang Changtai Agricultural Professional Cooperative Address before: 453000 Xinxiang, Henan, South Ring Road, No. 1 Applicant before: Xinxiang Crane Factory Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191108 Address after: 362103 No.117, Xinjie street, Xinxin village, Wangchuan Town, Quanzhou City, Fujian Province Patentee after: Chen Yijun Address before: Yongchun County of Quanzhou City, Fujian province 362614 Gui Yang Zhen Wen Tai Cun No. 139 Patentee before: Yongchun Guiyang Changtai Agricultural Professional Cooperative |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221219 Address after: 450103 Dongzhuang village, Guangwu Town, Xingyang City, Zhengzhou City, Henan Province Patentee after: ZHONGCHU HENGKE INTERNET OF THINGS SYSTEM CO.,LTD. Address before: 362103 No.117 Xinxin street, Xinxin village, Wangchuan Town, Quanzhou City, Fujian Province Patentee before: Chen Yijun |