CN109739080A - Control Method of Two-dimensional Servo Valve Stepping Electro-mechanical Converter Based on Neural Network - Google Patents
Control Method of Two-dimensional Servo Valve Stepping Electro-mechanical Converter Based on Neural Network Download PDFInfo
- Publication number
- CN109739080A CN109739080A CN201910043420.0A CN201910043420A CN109739080A CN 109739080 A CN109739080 A CN 109739080A CN 201910043420 A CN201910043420 A CN 201910043420A CN 109739080 A CN109739080 A CN 109739080A
- Authority
- CN
- China
- Prior art keywords
- signal
- current
- control
- formula
- angular displacement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 11
- 238000004804 winding Methods 0.000 claims abstract description 21
- 238000006073 displacement reaction Methods 0.000 claims abstract description 20
- 210000002569 neuron Anatomy 0.000 claims abstract description 17
- 230000003044 adaptive effect Effects 0.000 claims abstract description 7
- 230000005284 excitation Effects 0.000 claims abstract description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 230000005611 electricity Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 240000002627 Cordeauxia edulis Species 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 239000007787 solid Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 210000004218 nerve net Anatomy 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Electrically Driven Valve-Operating Means (AREA)
Abstract
The invention discloses a kind of control methods of two-dimentional servo valve step-by-step movement electromechanical converter neural network based.It the described method comprises the following steps: the method that current synchronization control is used to stepper motor；Position closed loop is using improved single neuron self-adaptive PID algorithm and feedforward compensation is added to obtain theoretical magnetic field angular displacement signal；Theoretical magnetic field angular displacement signal is limited to guarantee error angle within the scope of half of angular pitch；Theoretical magnetic field angular displacement signal is decomposed into each phase theoretical current signal；Current closed-loop uses mono-neural self-adaptive PID control algorithm, exports the pwm signal of two windings；Pwm signal control driving circuit generates the current signal of each phase winding, and the current signal of variation forms the movement of rotating excitation field control stepping motor rotor.The present invention can guarantee that rotor angular displacement accurate at an arbitrary position can quickly position, and have preferable anti-interference and adaptive ability.
Description
Technical field
The present invention relates to electromechanical control fields, more particularly to one kind based on neural network two dimension servo valve step-by-step movement electricity-
The control method of mechanical transducer.
Background technique
Two-dimentional servo valve is a kind of new structure servo valve that Zhejiang Polytechnical University Ruan Jian etc. was proposed in 2002, with respect to it
His servo valve has many advantages, such as that power-weight ratio is high, structure is simple, zero-bit leakage is small, contamination resistance is strong and dynamic property is good.
Two-dimentional servo valve is applied in many workplaces, such as airplane hydraulic pressure brake system, steering gear hydraulic system, electro-hydraulic tired
Exciter system, hydraulic catapult mechanism of labor testing machine etc..Two-dimentional servo valve using stepper motor as electromechanical converter,
The displacement signal of input is acted on spool by transmission mechanism by stepper motor when controlling two-dimentional servo valve, to control
The movement of spool.The Static and dynamic performance of stepper motor plays a key role the performance of two-dimentional servo valve.
In the prior art, to the control of two-dimentional servo valve step-by-step movement electromechanical converter frequently with closed-loop control, closed loop control
Link processed uses normal PID lgorithm, and although normal PID lgorithm has the advantages of simple structure and easy realization, but still there are certain limitations
Property, main cause is exactly the problem of pid parameter is adjusted, once after parameter tuning is good, parameter is not in entire control process
Become.But two-dimentional servo valve is in practical control process, since the disturbance that system will receive pressure etc. causes Parameters variation,
It is difficult to reach optimal control effect with constant pid parameter.
ANN Control is one of the front subject of automation field to grow up phase late 1980s, it
Control problem that is non-linear, not knowing, be uncertain of system to solve complicated opened up a new way.By with self study and adaptive
Should be able to power single neuron constitute single neural self-adaptive control intelligent PID controller, not only structure is simple, and adapts to environment
Variation, there is stronger robustness.
Summary of the invention
Based on this, in order to overcome normal PID lgorithm to be had in the control of two-dimentional servo valve step-by-step movement electromechanical converter
Parameter tuning is difficult, anti-interference difference and the problem of to the bad adaptabilities of different operating conditions, the present invention proposes a kind of based on mind
Control method through network two dimension servo valve step-by-step movement electromechanical converter.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of control method based on neural network two dimension servo valve step-by-step movement electromechanical converter, the control method
The following steps are included:
(1), input signal θ is acquiredi(t) with rotor actual displacement angle signal θ (t), deviation signal e is calculated；
(2), single neuron PID controller is constructed, single neuron PID controller is that PID control rule is incorporated nerve net
A kind of new controller of network realizes adaptive, self organizing function, the output u of controller by the adjustment to weighting coefficient
(k) expression formula are as follows:
In formula: xi(k)-controller input signal, w 'i(k)-weight coefficient, K-proportionality coefficient, k-sampling sequence number, xi
(k) expression formula are as follows:
Weight coefficient w 'i(k) adjustment is the expression formula by there is the Hebb learning rules of supervision to realize are as follows:
In formula: ηP、ηI、ηD- learning rate；
Proportional coefficient K is adjusted by a kind of nonlinear speed Control, and K value is automatic according to the absolute value of error originated from input
Adjustment, expression formula are as follows:
In formula: Kb,KaThe bound of-proportionality coefficient, nb,naThe corresponding deviation bound of-proportionality coefficient bound,
The bound of proportionality coefficient and the bound of deviation are determined according to Design space exploration method, the steps include:
Firstly, choose angle amplitude 1/2 is used as nbInitial value, choose angle amplitude 1/10 be used as naInitial value,
And solid this group of initial value, adjust Ka,Kb, determine steady-state error and Ka,KbRelationship, determine Ka,KbOptimal solution；
Then, the K in fixation in stepa,KbValue it is constant, adjust na,nb, obtain steady-state error and na,nbRelationship, determine
na,nbOptimal solution, finally determine the optimized parameter of the expression formula.
(3), output signal u (t), output signal u (t) are obtained according to the deviation signal and single neuron PID controller
Add feedforward compensation θi(t), theoretical magnetic field angular displacement signal θ is obtainedm(t), and to theoretical magnetic field angular displacement signal θm(t) it is limited
System with guarantee error angle within the scope of half of angular pitch, expression formula are as follows:
|θm(t)-Nrθ (t) | < π (6)
In formula: Nr- stepping motor the number of teeth；
(4), according to theoretical magnetic field angular displacement signal θm(t) Current Decomposition, the control of theory needed for obtaining corresponding windings are carried out
Electric current processed；
(5), each phase winding actual current is acquired, according to the theoretical control electric current and actual current, calculates each winding
Current deviation signal；
(6), according to the current deviation signal and single neuron PID controller, the pwm signal of each phase winding, PWM are exported
Signal control motor driving circuit generates corresponding current signal, and the current signal of variation forms rotating excitation field, to control electricity
The rotation of machine rotor.
Further, the stepper motor is two-phase hybrid stepping motor, and the phase difference of biphase current is 90 °, electric current point
Solution's expression are as follows:
In formula, ia(t)、ib(t)-diphase theory controls electric current；
Im- stepping motor winding current amplitude.
Technical concept of the invention are as follows: the prior art is same using electric current to two-dimentional servo valve step-by-step movement electromechanical converter
The method for walking control carries out double-closed-loop control to position and electric current, and closed loop uses normal PID lgorithm.But normal PID lgorithm controls
When parameter tuning is difficult, anti-interference is poor, and to the bad adaptability of different operating conditions.In response to this problem, it proposes using single nerve
First pid control algorithm not only has the preferable self study of neural network and adaptive ability, but also has regulatory PID control
Structure is simple, the characteristics of being easily achieved, realized before entering controller operation every time by the adjustment to weighting coefficient from
It adapts to, self organizing function.But the configuration of Proportional coefficient K value still needs manual adjustment, gives a fixed value every time, repeatedly
It adjusts, causes the process adjusted cumbersome tediously long.In response to this problem, it and proposes the method for using non-linear gearshift adjustment K value, makes K
Value is automatically adjusted according to the order of magnitude of error originated from input.Thereby realize the adaptive tune of all parameters of entire controller
Section.
Beneficial effects of the present invention are mainly manifested in: being realized the automatic adjusument of controller parameter, improved system
Anti-interference, system can be with the values of the variation automatically adjusting parameter of operating condition.
Detailed description of the invention
Fig. 1 is two-dimentional servo valve structural schematic diagram.
Fig. 2 is the control principle drawing of two-dimentional servo valve step-by-step movement electromechanical converter control method neural network based.
Fig. 3 is single neuron PID controller schematic diagram.
Fig. 4 is the algorithm flow chart of double-closed-loop control.
Specific embodiment
Below by taking two-dimentional servo valve two-phase hybrid stepping motor electromechanical converter as an example, in conjunction with attached drawing to this hair
It is bright to be further described.
Referring to Fig.1, Fig. 2, Fig. 3 and Fig. 4, it is a kind of based on neural network two dimension servo valve step-by-step movement electromechanical converter
Control method, the control method the following steps are included:
(1), input signal θ is acquiredi(t) and rotor actual displacement angle signal θ (t), input signal θi(t) turn reducing is practical
Angular displacement signal θ (t) obtains deviation signal e；
(2), single neuron PID controller is constructed, single neuron PID controller is that PID control rule is incorporated nerve net
A kind of new controller of network realizes adaptive, self organizing function, the output u of controller by the adjustment to weighting coefficient
(k) expression formula are as follows:
In formula: xi(k)-controller input signal, w 'i(k)-weight coefficient, K-proportionality coefficient, k-sampling sequence number, xi
(k) expression formula are as follows:
Weight coefficient w 'i(k) adjustment is the expression formula by there is the Hebb learning rules of supervision to realize are as follows:
In formula: ηP、ηI、ηD- learning rate；
Proportional coefficient K is adjusted by a kind of nonlinear speed Control, and K value is automatic according to the absolute value of error originated from input
Adjustment, expression formula are as follows:
In formula: Kb,KaThe bound of-proportionality coefficient, nb,naThe corresponding deviation bound of-proportionality coefficient bound,
The bound of proportionality coefficient and the bound of deviation are determined according to Design space exploration method, the steps include:
Firstly, choose angle amplitude 1/2 is used as nbInitial value, choose angle amplitude 1/10 be used as naInitial value,
And solid this group of initial value, adjust Ka,Kb, determine steady-state error and Ka,KbRelationship, determine Ka,KbOptimal solution；
Then, the K in fixation in stepa,KbValue it is constant, adjust na,nb, obtain steady-state error and na,nbRelationship, determine
na,nbOptimal solution, finally determine the optimized parameter of the expression formula.
(3), output signal u (t), output signal u (t) are obtained according to the deviation signal and single neuron PID controller
Add feedforward compensation θi(t), theoretical magnetic field angular displacement signal θ is obtainedm(t), and to theoretical magnetic field angular displacement signal θm(t) it is limited
System with guarantee error angle within the scope of half of angular pitch, expression formula are as follows:
|θm(t)-Nrθ (t) | < π (6)
In formula: Nr- stepping motor the number of teeth；
(4), according to theoretical magnetic field angular displacement signal θm(t) carry out Current Decomposition, two-phase hybrid stepping motor two-phase around
The current and phase difference of group is 90 °, the control of theory needed for decomposition obtains two phase windings electric current ia(t)、ib(t), expression formula are as follows:
In formula, ia(t)、ib(t)-diphase theory controls electric current；
Im- stepping motor winding current amplitude.
(5), two phase winding actual current i are acquiredaf(t)、ibf(t), theoretical current signal subtracts actual current signal and obtains two-phase
The current deviation signal e of windingia、eib；
(6), according to the current deviation signal eia、eibAnd single neuron PID controller, the PWM letter of two phase windings of output
Number, pwm signal controls motor-drive circuit, generates corresponding current signal, and the current signal of variation forms rotating excitation field, thus
Control the rotation of rotor.
In the present embodiment, double-closed-loop control has been carried out to position and electric current.Position-force control is to control stepping electricity
The position of machine rotor is consistent with input signal.Its control method is: stepping motor rotor actual displacement angle θ (t) is fed back
To input terminal and input signal θi(t) compare to form deviation signal, be obtained by deviation signal through single neuron PID controller operation
Theoretical magnetic field angular displacement signal θm(t).Current closed-loop is to control the actual current of two phase windings and its two-phase input current
It is consistent, thus the rotating excitation field of control stepping motor rotor movement required for obtaining.Its control method is: electric current is examined
The actual current i of two phase winding of stepper motor measured by slowdown monitoring circuitaf(t)、ibf(t) feed back after respectively with required theoretical current ia
(t)、ib(t) it is compared to form corresponding deviation signal, corresponding deviation signal is transported through respective single neuron PID controller
The pwm signal for generating two phase windings is calculated, then driving circuit is controlled by pwm signal, so that the electric current of two phase windings of control, obtains institute
The rotating excitation field needed, by the movement of rotating excitation field control stepping motor rotor.
Above-mentioned specific embodiment is used to explain the present invention, rather than limits the invention, in spirit of the invention
In scope of protection of the claims, to any modifications and changes that the present invention makes, protection scope of the present invention is both fallen within.
Claims (2)
1. a kind of control method based on neural network two dimension servo valve step-by-step movement electromechanical converter, which is characterized in that described
Control method the following steps are included:
(1), input signal θ is acquiredi(t) with rotor actual displacement angle signal θ (t), deviation signal e is calculated；
(2), single neuron PID controller is constructed, single neuron PID controller is that PID control rule is incorporated neural network
A kind of new controller realizes adaptive, self organizing function by the adjustment to weighting coefficient, the output u's (k) of controller
Expression formula are as follows:
In formula: xi(k)-controller input signal, w'i(k)-weight coefficient, K-proportionality coefficient, k-sampling sequence number, xi(k)
Expression formula are as follows:
Weight coefficient w'i(k) adjustment is the expression formula by there is the Hebb learning rules of supervision to realize are as follows:
In formula: ηP、ηI、ηD- learning rate；
Proportional coefficient K is adjusted by a kind of nonlinear speed Control, and K value is adjusted automatically according to the absolute value of error originated from input
It is whole, expression formula are as follows:
In formula: Kb,KaThe bound of-proportionality coefficient, nb,naThe corresponding deviation of-proportionality coefficient bound, proportionality coefficient it is upper
The bound of lower limit and deviation is determined according to Design space exploration method, the steps include:
Firstly, choose angle amplitude 1/2 is used as nbInitial value, choose angle amplitude 1/10 be used as naInitial value, and it is solid
This group of initial value adjusts Ka,Kb, determine steady-state error and Ka,KbRelationship, determine Ka,KbOptimal solution；
Then, the K in fixation in stepa,KbValue it is constant, adjust na,nb, obtain steady-state error and na,nbRelationship, determine na,nb
Optimal solution, finally determine the optimized parameter of the expression formula.
(3), output signal u (t) is obtained according to the deviation signal and single neuron PID controller, before output signal u (t) adds
Feedback compensation θi(t), theoretical magnetic field angular displacement signal θ is obtainedm(t), and to theoretical magnetic field angular displacement signal θm(t) limit with
Guarantee error angle is within the scope of half of angular pitch, expression formula are as follows:
|θm(t)-Nrθ (t) | < π (6)
In formula: Nr- stepping motor the number of teeth；
(4), according to theoretical magnetic field angular displacement signal θm(t) Current Decomposition, the control electricity of theory needed for obtaining corresponding windings are carried out
Stream；
(5), each phase winding actual current is acquired, according to the theoretical control electric current and actual current, calculates the electricity of each winding
Flow deviation signal；
(6), according to the current deviation signal and single neuron PID controller, the pwm signal of each phase winding, pwm signal are exported
Motor-drive circuit is controlled, corresponding current signal is generated, the current signal of variation forms rotating excitation field, turns to control motor
The rotation of son.
2. the control method according to claim 1 based on neural network two dimension servo valve step-by-step movement electromechanical converter,
It is characterized by: the stepper motor is two-phase hybrid stepping motor, the phase difference of biphase current is 90 °, Current Decomposition
Expression formula are as follows:
In formula, ia(t)、ib(t)-diphase theory controls electric current；
Im- stepping motor winding current amplitude.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910043420.0A CN109739080A (en) | 2019-01-17 | 2019-01-17 | Control Method of Two-dimensional Servo Valve Stepping Electro-mechanical Converter Based on Neural Network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910043420.0A CN109739080A (en) | 2019-01-17 | 2019-01-17 | Control Method of Two-dimensional Servo Valve Stepping Electro-mechanical Converter Based on Neural Network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109739080A true CN109739080A (en) | 2019-05-10 |
Family
ID=66365027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910043420.0A Pending CN109739080A (en) | 2019-01-17 | 2019-01-17 | Control Method of Two-dimensional Servo Valve Stepping Electro-mechanical Converter Based on Neural Network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109739080A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110429878A (en) * | 2019-07-23 | 2019-11-08 | 浙江工业大学 | A kind of double Auto-disturbance-rejection Controls of step motor type electromechanical converter |
| CN110932629A (en) * | 2019-12-20 | 2020-03-27 | 华中科技大学 | Inertia estimation method based on single neuron network and self-adaptive adjustment strategy thereof |
| CN114002947A (en) * | 2021-08-18 | 2022-02-01 | 华能澜沧江水电股份有限公司 | Double-cylinder adaptive control method, storage medium and controller for gate hydraulic hoist |
| CN116317748A (en) * | 2023-02-21 | 2023-06-23 | 成都创科升电子科技有限责任公司 | Double closed loop BLDC controller based on neuron proportional integral-fuzzy integral algorithm |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101834557A (en) * | 2010-04-29 | 2010-09-15 | 浙江工业大学 | Closed-loop Continuous Tracking Control Method of Stepping Motor Electromechanical Converter |
| US20140127996A1 (en) * | 2012-06-22 | 2014-05-08 | Fitbit, Inc. | Portable biometric monitoring devices and methods of operating same |
| CN107171612A (en) * | 2017-07-06 | 2017-09-15 | 桂林电子科技大学 | Fuzzy score rank PID switched reluctance machines method for controlling torque and system |
| CN107908101A (en) * | 2017-10-30 | 2018-04-13 | 王才旺 | A kind of simulating turntable control system based on Fuzzy Neural PID control |
| US9985439B2 (en) * | 2013-12-30 | 2018-05-29 | King Fahd University Of Petroleum And Minerals | Solar powered water pumping system with photovoltaic system that tracks a maximum power point |
-
2019
- 2019-01-17 CN CN201910043420.0A patent/CN109739080A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101834557A (en) * | 2010-04-29 | 2010-09-15 | 浙江工业大学 | Closed-loop Continuous Tracking Control Method of Stepping Motor Electromechanical Converter |
| US20140127996A1 (en) * | 2012-06-22 | 2014-05-08 | Fitbit, Inc. | Portable biometric monitoring devices and methods of operating same |
| US9985439B2 (en) * | 2013-12-30 | 2018-05-29 | King Fahd University Of Petroleum And Minerals | Solar powered water pumping system with photovoltaic system that tracks a maximum power point |
| CN107171612A (en) * | 2017-07-06 | 2017-09-15 | 桂林电子科技大学 | Fuzzy score rank PID switched reluctance machines method for controlling torque and system |
| CN107908101A (en) * | 2017-10-30 | 2018-04-13 | 王才旺 | A kind of simulating turntable control system based on Fuzzy Neural PID control |
Non-Patent Citations (1)
| Title |
|---|
| 王秀君等: "一种改进的单神经元PID控制策略", 《浙江大学学报（工学版）》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110429878A (en) * | 2019-07-23 | 2019-11-08 | 浙江工业大学 | A kind of double Auto-disturbance-rejection Controls of step motor type electromechanical converter |
| CN110932629A (en) * | 2019-12-20 | 2020-03-27 | 华中科技大学 | Inertia estimation method based on single neuron network and self-adaptive adjustment strategy thereof |
| CN114002947A (en) * | 2021-08-18 | 2022-02-01 | 华能澜沧江水电股份有限公司 | Double-cylinder adaptive control method, storage medium and controller for gate hydraulic hoist |
| CN114002947B (en) * | 2021-08-18 | 2023-12-01 | 华能澜沧江水电股份有限公司 | Double-cylinder self-adaptive control method for gate hydraulic hoist, storage medium and controller |
| CN116317748A (en) * | 2023-02-21 | 2023-06-23 | 成都创科升电子科技有限责任公司 | Double closed loop BLDC controller based on neuron proportional integral-fuzzy integral algorithm |
| CN116317748B (en) * | 2023-02-21 | 2023-11-07 | 成都创科升电子科技有限责任公司 | Double closed loop BLDC controller based on neuron proportional integral-fuzzy integral algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109739080A (en) | Control Method of Two-dimensional Servo Valve Stepping Electro-mechanical Converter Based on Neural Network | |
| CN109756166B (en) | Parameter setting method for dual closed-loop vector control PI (proportional integral) regulator of permanent magnet synchronous motor | |
| WO2018120323A1 (en) | Servo control strategy which simultaneously eliminates counter potential and load torque disturbances and system thereof | |
| Low et al. | Robust model predictive control and observer for direct drive applications | |
| CN109412492B (en) | Speed loop control parameter self-tuning method based on fuzzy equivalent input interference method | |
| Souza et al. | Optimal LQI and PID synthesis for speed control of switched reluctance motor using metaheuristic techniques | |
| CN109507869A (en) | A kind of optimization method of the motor control PI parameter suitable for permanent magnet synchronous motor | |
| Li et al. | Design of PMSLM position controller based on model predictive control algorithm | |
| Li et al. | Improved active disturbance rejection control of permanent-magnet synchronous motor based on BP neural network | |
| Amini et al. | Robust H2 and H∞ controller design for DC position motor control under uncertainties | |
| Wang et al. | Double closed loop control for BLDC based on whole fuzzy controllers | |
| CN109507873A (en) | A kind of bandwidth parameter DC speed regulation feedback control system | |
| CN109217756A (en) | Based on mixing artificial neural network reference adaptive Vector Control System of Induction Motor method | |
| Abd Elhamid | Cascade control system of direct current motor | |
| Ouddah et al. | Fixed structure H∞ loop shaping control of switched reluctance motor for electrical vehicle | |
| Fodor et al. | Compensation of parameters variations in induction motor drives using a neural network | |
| Manuaba et al. | Coordination of PID based power system stabilizer and AVR using combination bacterial foraging techique—Particle swarm optimization | |
| CN115629546A (en) | Neural network sliding mode self-adaptive control method and device for motor | |
| Tapia et al. | On-line speed control of the shunt-connected DC motor via a neurocontroller | |
| Xia et al. | Adaptive PID control and on-line identification for switched reluctance motors based on BP neural network | |
| Skultéty et al. | Predictive synchronous generator excitation control based on Laguerre model | |
| Dodds et al. | A robust forced dynamic sliding mode minimum energy position controller for permanent magnet synchronous motor drives | |
| Jinggang et al. | A new antiwindup speed controller for induction motor drive system | |
| Alasooly et al. | Control of DC motor using different control strategies | |
| CN116800145A (en) | Fractional order PI control method applied to three-stage generator |
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: 20190510 |