CN101917150A - Robust controller of permanent magnet synchronous motor based on fuzzy-neural network generalized inverse and construction method thereof - Google Patents
Robust controller of permanent magnet synchronous motor based on fuzzy-neural network generalized inverse and construction method thereof Download PDFInfo
- Publication number
- CN101917150A CN101917150A CN2010102094452A CN201010209445A CN101917150A CN 101917150 A CN101917150 A CN 101917150A CN 2010102094452 A CN2010102094452 A CN 2010102094452A CN 201010209445 A CN201010209445 A CN 201010209445A CN 101917150 A CN101917150 A CN 101917150A
- Authority
- CN
- China
- Prior art keywords
- neural network
- current
- fuzzy neural
- linear
- pseudo
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 102
- 230000001360 synchronised effect Effects 0.000 title claims abstract description 31
- 238000010276 construction Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 29
- 230000006870 function Effects 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000012546 transfer Methods 0.000 claims abstract description 16
- 230000002068 genetic effect Effects 0.000 claims abstract description 12
- 150000001875 compounds Chemical class 0.000 claims abstract description 4
- 239000002131 composite material Substances 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 24
- 238000001514 detection method Methods 0.000 claims description 23
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 230000009466 transformation Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 4
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 230000005284 excitation Effects 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 238000003786 synthesis reaction Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 9
- 238000013178 mathematical model Methods 0.000 description 7
- 210000002569 neuron Anatomy 0.000 description 7
- 230000001105 regulatory effect Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000004907 flux Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000087 stabilizing effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013329 compounding Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 239000006247 magnetic powder Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000033772 system development Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Control Of Electric Motors In General (AREA)
- Control Of Ac Motors In General (AREA)
Abstract
The invention discloses a robust controller of a permanent magnet synchronous motor based on a fuzzy-neural network generalized inverse and a construction method thereof. The construction method of the invention comprises the following steps of: combining an internal model controller and a fuzzy-neural network generalized inverse to form a compound controlled object; serially connecting two linear transfer functions and one integrator with the fuzzy-neural network with determined parameters and weight coefficients to form the fuzzy-neural network generalized inverse, serially connecting the fuzzy-neural network generalized inverse and the compound controlled object to form a generalized pseudo-linear system, linearizing a PMSM (permanent magnet synchronous motor), and decoupling and equalizing the linearized PMSM into a second-order speed pseudo-linear subsystem and a first-order current pseudo-linear subsystem; and respectively introducing an internal-model control method in the two pseudo-linear subsystems to construct the internal model controller. The robust controller of the invention has the advantages of overcoming the dependence and local convergence of the optimal gradient method on initial values and solving the problems of randomness and probability caused by using the simple genetic algorithm, obtaining the high performance control, anti-disturbance performance and adaptability of the motor and simplifying the control difficulty, along with simple structure and high system robustness.
Description
Technical Field
The invention relates to a permanent magnet synchronous motor controller, which is suitable for robust control of driving a permanent magnet synchronous motor by a voltage source type inverter and belongs to the technical field of power transmission control equipment.
Background
Permanent Magnet Synchronous motors (PMSM for short) have been widely used in the fields of aerospace, weapon defense, numerical control machines, industrial robots, flexible control, communication industry, oil field and chemical industry, and long-running-time fans and pumps.
The control method of the permanent magnet synchronous motor speed regulating system mainly comprises constant voltage-frequency ratio control, vector control, direct torque control, differential geometric state feedback control and the like. The permanent magnet synchronous motor speed regulation system based on the steady-state model in the constant-voltage frequency ratio control mode is simple in structure, low in cost, easy to implement and capable of meeting general speed regulation requirements, but the system performance is not high, the system excessively depends on a system dynamic mathematical model, open-loop control is achieved, the load capacity at low speed is limited, the out-of-step phenomenon is easy to occur when load or speed instructions are suddenly added, and ideal dynamic control performance cannot be obtained. The permanent magnet synchronous motor speed regulating system based on the dynamic model in the vector control mode has the advantages of good dynamic performance, wide speed regulating range, high control precision and the like, is approximately decoupled in a stable state, and is gradually widely applied to the field of industrial dragging. The permanent magnet synchronous motor speed regulating system based on the stator flux linkage orientation direct torque control mode is convenient to realize full digitalization, an alternating current motor and a direct current motor do not need to be equivalent, complex rotating coordinate transformation and a motor model are omitted, the problem that the control effect is influenced by the change of rotor parameters in vector control does not need to be considered, only stator resistance is required to be detected and the stator flux linkage of the motor is required to be observed, partial dynamic decoupling is realized by using the comparison of torque and flux linkage hysteresis, and the defects of poor low-speed performance, large torque pulsation and the like exist. The differential geometry method is a method for decoupling and controlling nonlinear systems in a linear mode, which is developed by taking differential geometry as a tool, and aims to convert complex systems into simple linear systems after the nonlinear systems are subjected to accurate linearization processing, so that linear controllers can be analyzed and designed by using a linear theory in a wider working domain under the condition of not losing the controllability and accuracy of the systems.
At present, although a neural network inverse system control method can realize linear decoupling of a permanent magnet synchronous motor, a plurality of integral pseudo linear subsystems formed after decoupling are open-loop unstable, the neural network based on experience risk minimization has the defects of local minimum points, over-learning, excessive dependence on experience on selection of structure and type and the like, and meanwhile, the permanent magnet synchronous motor has load mutation, more system controllable parameters, unmodeled dynamic influence, easy desynchronization and the like in actual operation, and the uncertain factors cause model mismatch to enable the system to deviate from an expected control target.
Disclosure of Invention
Because the dynamic model for controlling the permanent magnet synchronous motor is a nonlinear and strongly coupled multivariable time-varying system, in order to overcome the defects of several basic control methods in the prior art, the invention provides the fuzzy neural network generalized inverse robust controller for the permanent magnet synchronous motor, which realizes the linear decoupling control of the permanent magnet synchronous motor, well inhibits parameter perturbation and load disturbance, overcomes the interference of unmodeled dynamic, improves the dynamic response speed and the steady-state tracking precision of the speed regulating system of the permanent magnet synchronous motor, and realizes high-performance robust control.
The invention also aims to provide a construction method of the generalized inverse robust controller of the fuzzy neural network, which is used for comprehensively processing a plurality of decoupled pseudo-linear subsystems and ensuring the control effect of the permanent magnet synchronous motor.
The controller adopts the technical scheme that: the fuzzy neural network generalized inverse combination system is formed by combining an internal model controller and a fuzzy neural network generalized inverse; the internal model controller is formed by connecting a speed internal model controller and a current internal model controller in parallel, the speed internal model controller is formed by connecting a speed internal model and a speed controller, and the current internal model controller is formed by connecting a current internal model and a current controller; the fuzzy neural network generalized inverse and the composite controlled object are connected in series to form a generalized pseudo linear system, and the generalized pseudo linear system is equivalent to 1 speed sub linear system and 1 current sub linear system; the generalized inverse of the fuzzy neural network consists of a five-layer fuzzy neural network with 5 input nodes and 2 output nodes, two 2 linear transfer functions and 1 integrator; the composite controlled object comprises a current speed detection and calculation module and an extended inverter control part for driving the PMSM, wherein the extended inverter control part is formed by connecting an inverse Park conversion and a voltage source type inverter in an SVPWM (space vector pulse width modulation) debugging mode, the current speed detection and calculation module comprises a current speed calculation part, a Park conversion, a Clarke conversion and a photoelectric encoder, and the Clarke conversion and the photoelectric encoder are connected with the PMSM.
The construction method of the controller sequentially comprises the following steps: firstly, Clarke transformation, Park transformation and a third-order model are equivalent to form PMSM, and the PMSM forms a whole composite controlled object through a current speed detection and calculation module and an extended inverter control part; then 2 linear transfer functions, 1 integrator and a fuzzy neural network determining each parameter and weight coefficient are connected in series to form a fuzzy neural network generalized inverse, the fuzzy neural network generalized inverse and a composite controlled object are connected in series to form a generalized pseudo linear system, and the generalized pseudo linear system linearizes and decouples the PMSM and is equivalent to a 1 second-order velocity pseudo linear subsystem and a 1 first-order current pseudo linear subsystem; and finally, respectively introducing the second-order velocity pseudo-linearity subsystem and the first-order current pseudo-linearity subsystem into an internal model control method to construct an internal model controller, combining the internal model controller with the generalized pseudo-linearity system to form a fuzzy neural network generalized inverse robust controller, and controlling the composite controlled object.
The invention has the beneficial effects that:
1. the fuzzy neural network has the advantages of strong self-learning capability, parallel computing capability, nonlinear approximation capability, strong fuzzy reasoning capability of fuzzy logic and the like, is combined with the linear decoupling characteristic of an inverse system, and improves the learning capability of the neural network by utilizing the fuzzy logic technology; extracting fuzzy rules or adjusting fuzzy rule parameters by using the learning capacity of the neural network; and a neural network is utilized to realize a fuzzy logic system and parallel fuzzy reasoning. The combination overcomes the influence of unmodeled dynamics of a control system, has strong robustness and fault tolerance, converts the control problem of a complex multivariable two-input two-output nonlinear coupling system of a permanent magnet synchronous motor into the control problem of two stable pseudo linear subsystems, further reasonably constructs a linear closed-loop controller, can obtain high-performance control and anti-load disturbance and adaptivity of the motor, and greatly simplifies the control difficulty.
2. The generalized inverse control system of the composite controlled object is constructed by the fuzzy neural network, the transfer function and the integrator, completely gets rid of the dependence of the traditional control method on the mathematical model and the parameters of the controlled system of the permanent magnet synchronous motor, effectively overcomes the instability of the integral fuzzy neural network inverse system, solves the control problem caused by the difficult measurement of the partial state of the original high-order controlled system, is a major breakthrough of the control method of the traditional inverse system, and the pseudo wire generalized inverse system which is formed by compounding the generalized inverse system and the original system not only can realize the linear decoupling of the original system, but also can reasonably configure the poles of the pseudo wire subsystem formed after the decoupling in a complex plane by reasonably adjusting the parameters of a linear link, obtain more ideal open-loop frequency characteristics, realize the large-scale linearization, the decoupling and the order reduction, thereby being capable of conveniently constructing the controller according to the linear control theory to carry out high-precision control, the method is beneficial to the synthesis of the system, simple in structure, high in system robustness and easy for engineering realization.
3. The method for determining and adjusting the fuzzy neural network parameters and the weight is the combination of a genetic algorithm and an optimal gradient method. The traditional fuzzy neural network simply uses an optimal gradient algorithm, although the implementation is simple and the local searching capability is strong, the online learning period is long, the algorithm convergence speed is slow, and the defects of local minimum values and the like are easily caused; the genetic algorithm is used as a global search and optimization technology, although the genetic algorithm cannot express knowledge, the genetic algorithm has strong learning capacity and optimization capacity, meanwhile, the genetic algorithm has global parameters and a network structure, about 90% of an optimal solution can be searched at a high speed, but the later search variation probability is small, the group diversity is difficult to maintain, the implementation is complex, and the method is not as good as an optimal gradient method in occasions needing real-time control. Combining the two methods, and making up for the deficiencies, on one hand, the genetic algorithm ensures the global convergence of network learning, and overcomes the problems of the dependence of the optimal gradient method on the initial value and the local convergence; on the other hand, the optimal gradient learning ensures the local searching capability, has strong online adjustment capability and simple realization, overcomes the problems of randomness and probability caused by a pure genetic algorithm, and is beneficial to improving the searching probability.
4. Based on a dSPACE real-time simulation system as an experimental platform, the system realizes complete seamless connection with MATLAB/Simulink/RTW. The dSPACE real-time system has the advantages of strong real-time performance, high reliability, good expandability and the like. The processor in the dSPACE hardware system has high-speed computing capability and is provided with rich I/O support, and a user can combine the processors as required; the software environment is powerful and convenient to use, and comprises a complete set of tools for realizing automatic code generation/downloading and testing/debugging. The high-precision rotating speed control of the permanent magnet synchronous motor can be realized by utilizing a powerful software and hardware experimental platform, a set of parallel engineering from concept design to mathematical analysis and test of a control algorithm of the motor, realization of a real-time simulation test to monitoring and adjusting of an experimental result is completed, the research and development period is short, resources are saved, the function is powerful, and the realization is easy.
5. The invention can be applied to other types of motors such as synchronous motors, direct current motors, asynchronous motors and the like, and has wide application prospect in a synchronous coordination control system taking a plurality of networked alternating current motors (a plurality of motors) as power devices.
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Drawings
Fig. 1 is a connection diagram of the permanent magnet synchronous motor body PMSM1 and the current speed detection and calculation module 31.
Fig. 2 is a diagram of the structure of the composite controlled object 3 composed of the PMSM1, the extended inverter control part 32, and the current speed detection and calculation module 31, and a simplified equivalent model thereof.
FIG. 3 is a diagram of the structure of the generalized inverse system 4 of the fuzzy neural network and its equivalent model;
FIG. 4 is a diagram of a generalized pseudo-linear system 5 structure and its equivalent two sub-linear systems;
fig. 5 is a structural diagram of the generalized inverse robust controller 7 of the fuzzy neural network of the present invention.
Fig. 6 is a schematic block diagram of the generalized inverse robust controller 7 of the fuzzy neural network of the present invention, which uses the dSPACE experimental platform to implement the control system.
Detailed Description
As shown in fig. 5, the fuzzy neural network generalized inverse robust controller 7 of the present invention controls the composite controlled object 3. The fuzzy neural network generalized inverse robust controller 7 is formed by combining the internal model controller 6 and the fuzzy neural network generalized inverse 4. The internal model controller 6 is formed by connecting a speed internal model controller 61 and a current internal model controller 62 in parallel, wherein the speed internal model controller 61 is formed by connecting a speed internal model 611 and a speed controller 612; the current internal model controller 62 is formed by connecting a current internal model 621 and a current controller 622. Meanwhile, the generalized inverse 4 of the fuzzy neural network in the generalized inverse robust controller 7 of the fuzzy neural network and the composite controlled object 3 are connected in series to form a generalized pseudo linear subsystem 5, and the original high-order nonlinear coupling system is decoupled and equivalent to 1 second-order velocity pseudo linear subsystem 51 and 1 first-order current pseudo linear subsystem 52. Further, the generalized inverse 4 of the fuzzy neural network is formed by adopting a five-layer fuzzy neural network 41 with 5 input nodes and 2 output nodes, two 2 linear transfer functions and 1 integrator on the basis of analyzing the generalized reversibility of the PMSM1 aiming at the coupling among the motor speed, the motor voltage and the stator current according to an equivalent mathematical model of the PMSM 1. The composite controlled object 3 is formed by connecting a PMSM1, a current speed detection and calculation module 31 and an extended inverter control part 32, the extended inverter control part 32 formed by combining an inverse Park conversion and a voltage source type inverter in an SVPWM (space vector pulse width modulation) debugging mode drives a PMSM1, and the composite controlled object is simultaneously connected with a current speed detection part formed by a current speed calculation part, a Park conversion, a Clarke conversion and a photoelectric encoder 2The measuring and calculating module 31 is integrated into a whole. The PMSM1 is formed by Clarke transformation, Park transformation and a third-order model in an equivalent mode, wherein the third-order model is a third-order differential equation set under a d-q coordinate system. The formed current speed detection and calculation module 31 is not only an important component of the composite controlled object 3, but also a signal feedback link in which the current, the rotating speed and the rotor displacement are used as internal model control and Park conversion. It should be noted that: the current signal actually output by the controlled object is the square of the stator current
Hereinafter, the stator currents will be referred to as stator currents.
The construction method of the generalized inverse robust controller 7 of the fuzzy neural network comprises the following steps: firstly, based on a PMSM1, a current speed detection and calculation module 31 composed of a current speed calculation part, Clarke, Park conversion and a photoelectric encoder 2 and an extended inverter control part 32 composed of a voltage source type inverter under an inverse Park conversion and SVPWM modulation mode form a whole to form a composite controlled object 3 to drive a load. Secondly, a generalized inverse 4 of the fuzzy neural network with 2 input nodes and 2 output nodes, which is composed of 5 input nodes and 2 output nodes of the fuzzy neural network 41(5 layers of networks) and 2 linear transfer functions and 1 integrator, is connected with the composite controlled object 3 in series to form a generalized pseudo-linear system 5, so that a multivariable and strongly coupled high-order nonlinear system of the PMSM1 is linearized and decoupled and is equivalent to a 1 second-order velocity pseudo-linear subsystem 51 and a 1 first-order current pseudo-linear subsystem 52, and the parameter a of the linear transfer function is reasonably adjustedj0，aj1，……，
The poles of each pseudo linear subsystem formed after decoupling are reasonably configured in the complex plane, and the conversion from the integral unstable subsystem to the stable subsystem is realized. On the basis, the second-order velocity pseudo-linearity subsystem 51 and the first-order current pseudo-linearity subsystem 52 are respectively introduced into an internal model control method to construct the internal model controller 6, the internal model controller 6 is reasonably designed,the generalized pseudo linear system 5 is combined to form a fuzzy neural network generalized inverse robust controller 7 to control the composite controlled object 3, high-precision robust control of the PMSM1 is achieved, dynamic interference of unmodeled models is overcome, and the system has excellent dynamic and static control performance, anti-interference capability and high-precision tracking performance. Different hardware or software implementations may be used depending on different control requirements. Specifically described with the following 7 steps:
step 1: as shown in fig. 1, a current speed detection and calculation module 31 is constructed. Two-phase stator current i in control signal of PMSM1sA、isBTwo-phase stator current i obtained by Hall element detectionsA、isBI is obtained by Clarke transformation and Park transformationsd、isqThe photoelectric encoder 2 detects a rotation speed signal obtained by PMSM1 and isd、isqA current signal i outputted after being operated by the current velocity calculating sections 2＝isd 2+isq 2Angular velocity ω of rotorrAnd angular displacement θ as an output of the current speed detection and calculation module 31. The current speed detection and calculation module 31 serves both as an output of the composite controlled object 3 described below and provides a feedback signal to the internal model controller 6.
Step 2: as shown in fig. 2, a composite controlled object 3 of the PMSM1 is constructed. The composite controlled object 3 is formed by connecting the extended inverter control section 32, the mathematical model of the equivalent PMSM1, and the current detection and calculation module 31. The whole body of the extended inverter control part 32 and the PMSM1 is equivalent, so that the similar equivalent is a controlled direct current motor; the extended inverter control part 32 is composed of an inverse Park conversion and a voltage source type inverter under an SVPWM modulation mode, and is connected with a mathematical model of PMSM1 in series; the mathematical model of the PMSM1 is composed of a Clarke transformation, a Park transformation and a direct current model in series, but is actually connected with the controller, namely the PMSM1 body. The input of the composite controlled object 3 is a stator voltage in a d-q two-phase rotating coordinate system, i.e., u ═ q1，u2]T＝[usd，usq]TTo transportDerived as rotor angular velocity and two-phase stator current signals, i.e. y ═ y1，y2]T＝[ωr，is 2]T. Wherein u issd、usqD-axis voltage and q-axis voltage under the two-phase rotating coordinate system are respectively used as input signals of the composite controlled object 3 and output signals for system reversibility analysis; omegar、isThe rotor angular speed and stator current signals respectively output by the PMSM1 are also important components of the system reversibility analysis input signal.
Step 3: as shown in fig. 2 to 3, a mathematical model of the whole composite controlled object 3 of the permanent magnet synchronous motor in a vector control mode is obtained through analysis, equivalence and derivation and is a two-phase rotating coordinate system, namely a three-order nonlinear differential equation set in a d-q coordinate system, the existence of a generalized inverse system of the three-order differential equation set is proved according to an inverse system theory, the relative order of a vector is {2, 1}, the generalized inverse of the system is further deduced, a generalized inverse system model of the permanent magnet synchronous motor is established, a method basis is provided for the generalized inverse 4 of a fuzzy neural network, and 2 input quantities are determined to be 2 input quantities respectively
The 2 outputs are respectively the input u ═ u of the composite controlled object 31，u2]T＝[usd，usq]T. Wherein,
andtwo input quantities of the generalized inverse system 4 of the fuzzy neural network are respectively,
and
is the rotor angular velocity and two-phase stator current signal y in step 21And y2And the linear resultant of their derivatives of each order, a10、a11、a12、a20And a21Respectively, are coefficients.
Step 4: as shown in fig. 3, the fuzzy neural network 41 plus 2 linear transfer functions and 1 integrator are used to construct the generalized inverse 4 of the fuzzy neural network, which provides a basis for the learning training of the fuzzy neural network 41. According to the specific situation of PMSM1, parameter a of generalized inverse 4 linear transfer function of fuzzy neural network is reasonably adjusted10，a11，a12，a20，a21The dynamic characteristic of the generalized inverse system is represented, the poles of the single-input single-output pseudo linear subsystem formed after decoupling are reasonably configured in a complex plane, the conversion from an integral unstable subsystem to a stable subsystem is realized, and the open-loop linear stable control of the nonlinear system is realized. Wherein the fuzzy neural network 41 adopts a five-layer network. The first layer is an input layer, the number of input nodes is 5, neurons are input nodes and represent input linguistic variables, and the first layer is only used for transmitting signals to the next layer, namely f1＝ui (1)，a1＝f1(fzAnd azNet input and activation functions representing nodes of the z-th layer, respectively, z being 1, 2, 3, 4, 5; u. ofi (1)Where (1) and i represent the ith input of the first level node neuron, and so on), the weight wij (1)1 (representing the connection weight coefficient of the ith input linguistic variable to the next layer j neuron); a second layer of fuzzy layer with 15 nodes, each node representing a language variable value for calculating membership function of each input component, and local layer of neurons selecting Gaussian function as excitation function
，f2＝-(ui (2)-mij)2/σij 2(mijAnd σijThe center and width of the Gaussian function of the jth item of the ith input linguistic variable respectively), each neuron outputs a corresponding membership function, and the weight wij (2)＝mij(ii) a The third layer is a rule layer, the number of nodes is 9, the nodes are used for generating fuzzy logic rules and matching with the front piece, namely calculating the fitness of each rule, and the neuron nodes in the layer execute fuzzy and operation corresponding positions and operation, namely f3＝min{u1 (3)，u2 (3)，……u5 (3)}，a3＝f3Weight wij (3)1 is ═ 1; a fourth normalization layer, the number of nodes is 9, the network connection defines the conclusion of the rule nodes, the output generated by each rule corresponding to the input is generated, the matching is a back-piece matching, and the OR operation is executed, namely
a4＝min{1，f4} (p represents the input number of neuron nodes), and weight wij (4)1 is ═ 1; a fifth layer of deblurring (output layer) with 2 nodes for deblurring, performing sharpening calculation, and generating the total output of control rules, i.e. the output layer
Weight wij (5)＝mijσij. Of the 5 input nodes, the first input of the generalized inverse 4 of the fuzzy neural network
As a first input to the fuzzy neural network 41; it is passed through a second order system s/a10s2+a11s+a12(the second order system is a second order linear element G connected to the fuzzy neural network 411(s)s，a10、a11、a12Coefficients of a linear transfer function) are output asI.e. the second input of the fuzzy neural network 41; then passes through 1 integrator s-1Output y1I.e. the third input of the fuzzy neural network 41; second input of generalized inverse 4 of fuzzy neural networkAs a fourth input to the fuzzy neural network 41; it is passed through a first order system 1/a20s+a21(the first order system is a first order linear element G connected to the fuzzy neural network 412(s)，a20、a21Coefficients that are first order elements) are output as y2I.e. the fifth input of the fuzzy neural network 41. Thus, the fuzzy neural network 41, 2 linear transfer functions and 1 integrator form the fuzzy neural network generalized inverse 4, and the output of the fuzzy neural network 41 is the output of the fuzzy neural network generalized inverse 4.
Step 5: as shown in fig. 3, the adjustment and determination of the parameters and weight coefficient values of the fuzzy neural network 41. The learning of the fuzzy neural network 41 is divided into two stages of off-line learning and on-line weight coefficient adjustment by combining a genetic algorithm and an optimal gradient method. The method comprises the following steps: phi step excitation signal usd，usqRespectively adding the signals to 2 input ends of a composite controlled object 3, and acquiring the rotor angular speed omega of the PMSM1 in a sampling period of 5msrAnd current isA，isBObtaining the required data through the current speed detection and calculation module 31
And storing; ② data signal to be storedRespectively off-line obtaining first and second derivatives of speed
First derivative of sum current
This time is: y is1＝ωr，
Further, the method in step 3 is used to obtain
And the signals are normalized to form a training sample set of the fuzzy neural network 41
Thirdly, the fuzzy neural network 41 is trained off-line by using the genetic algorithm, the parameters of the membership functions and the output initial weight are roughly adjusted, wherein the cross probability PcAnd the mutation probability PmThe convergence condition (P) of the algorithm is measured by adopting an adaptive mode and using a proper functionc＝k1/(fmax-f)，Pm＝k2/(fmax-f)，fmaxAnd f represents the maximum and average fitness in the population, respectively, k1、k2Positive and real coefficients with the size of 0-1), setting the termination evolution algebra as G300, and then obtaining a global approximate solution, wherein the specific training step is similar to that of a general genetic algorithm, and roughly determining each parameter and weight coefficient of the fuzzy neural network 41; then, when the controller is operated, the parameters of the fuzzy neural network 41 are refined and adjusted on line in real time by adopting an error back-propagation optimal gradient method which drives the quantitative term and the learning rate, so that the output mean square error precision of the fuzzy neural network 41 is kept within 0.0005.
Step 6: as shown in fig. 4, a fuzzy neural generalized pseudo-linear system 5 is formed, and the original composite controlled object 3 is linearized and decoupled to be equivalent to 1 speed sub-linear system 51 and 1 current sub-linear system 52. Firstly, 2 linear transfer functions and 1 integrator are connected in series with a fuzzy neural network 41 which determines each parameter and weight coefficient to form a fuzzy neural network generalized inverse 4, as shown by a small dashed box on the left of fig. 4; then, the generalized inverse 4 of the fuzzy neural network and the composite controlled object 3 are connected in series to form a generalized pseudo-linear system 5, as shown by a large dashed box in the left diagram of fig. 4, the generalized pseudo-linear system 5 is formed by connecting 1 second-order velocity pseudo-linear subsystem 51 and 1 first-order current pseudo-linear subsystem 52 in parallel and equivalently, as shown in the right diagram of fig. 4, the input of the equivalent 1 second-order velocity pseudo-linear subsystem 51 and 1 first-order current pseudo-linear subsystem 52 are respectively the input of the equivalent 1 second-order velocity pseudo-linear subsystem 51 and the equivalent 1 first-order current pseudo-linear subsystem 52
Namely two input quantities of generalized inverse 4 of the fuzzy neural network, and the corresponding outputs are respectively omegar，
Namely, the current and the rotor angular velocity output by the current velocity detection and calculation module 31, so that the control of the original high-order and coupled nonlinear complex system is converted into the simple linear system control.
And 7, a step: and constructing a generalized inverse robust controller 7 of the fuzzy neural network. According to the 2 nd and 3 rd steps, the relative system order is {2, 1}, and according to the 6 th step, the input of the generalized pseudo-linear system 5 compounded by the generalized inverse 4 of the fuzzy neural network and the compound controlled object 3 is shown as
The fuzzy neural network generalized inverse robust controller 7 is constructed by combining the properties of the two pseudo-linear subsystems, namely the speed pseudo-linear subsystem 51 and the current pseudo-linear subsystem 52, the interference faced in actual operation and the time-varying characteristics of parameters. The invention designs the generalized inverse robust controller 7 of the fuzzy neural network by adopting design methods such as an internal model control principle, a Lyapunov (Lyapunov) theory and the like in a linear system robust control theory. The internal model controller 6 is composed of a linearized speed internal model controller 61 and a current internal model controller 62. D1(s) and D2(s) are interference signals of two controllers respectively, the speed internal model controller 61 is composed of a speed internal model 611 and a speed controller 612, and the current internal model controller 62 is composed of a current internal model 621 and a current controller 622. By selecting the parameter a appropriately10，a11，a12，a20，a21Let the internal expected model 611 of the second order linear velocity subsystem be G1m(s)＝1/(a10s2+a11s+a12)＝1/(s2+1.414s +1), then the corresponding velocity controller 612 is designed toThe internal expectation model 621 of the first order current linear subsystem is G2m(s)＝1/(a20s+a21) 1/(s +1), it is also possible to design the corresponding current controller 622 as
Wherein, a10、a12、a11Transfer function G for velocity internal expectation model 6111m(s) coefficient of a10＝a12＝1，a111.414, internal model G now1m(s) is a typical second order stable linear system; f1(s) a low pass filter of type I for the corresponding velocity controller 612, F1(s)＝1/(0.5s+1)2；a20、a21Coefficient of transfer function of the current internal expectation model 621, which is a20＝a21＝1；F2(s) a low pass filter of type I of the corresponding current controller 622, F2(s) ═ 1/(2s + 1)). The structure and connection of the whole fuzzy neural network generalized inverse robust controller 7 are shown in fig. 5.
An implementation schematic diagram of the whole permanent magnet synchronous motor speed regulating system based on the fuzzy neural network generalized inverse robust controller 7 on a dSPACE real-time simulation and test system experiment platform is shown in fig. 6. In fig. 7, there are PMSM1 and dSPACE 81, and the accessory modules include an analog input ADC module, an analog output DAC module, a signal detection part, a photoelectric encoder disk 2, a hall element, a magnetic powder brake unit, an industrial control display module 83 and an intelligent power module IPM 82; the software environment mainly comprises real-time code generation download software RTI, comprehensive experiment and test environment software ControlDesk and Simulink simulation software. The fuzzy neural network generalized inverse robust controller 7 adopts dSPACE implementation to control the composite controlled object 3. The experiment control program is downloaded to the dSPACE control panel by the upper computer, an experiment starting signal is sent out through a ControlDesk visual control interface, and the control system operates independently; 6 paths of PWM control signals output by the control board are transmitted to the intelligent power module driving motor; the detection part collects current, voltage, speed and protection signals and feeds the signals back to the control panel and stores the signals for control effect analysis, and parameters can be modified off-line or on-line to control the motor so as to achieve high-precision stable operation and shorten the system development period.
The invention realizes the linearization decoupling control of a multivariable and strong-coupling time-varying nonlinear system of the permanent magnet synchronous motor by constructing the fuzzy neural network generalized inverse, converts the control problem of a complex system with mutually coupled stator current, voltage and speed into the control problem of a simple second-order speed linear stabilizing subsystem and a first-order current linear stabilizing subsystem, combines the internal model control principle, conveniently and reasonably designs a robust controller, realizes the high-precision robust control of the rotating speed of the permanent magnet synchronous motor, overcomes the dynamic interference of the system without modeling, and ensures that the system has excellent dynamic and static performances, anti-interference and high-precision tracking performance.
Claims (3)
1. A fuzzy neural network generalized inverse robust controller of a permanent magnet synchronous motor is characterized in that: the fuzzy neural network generalized inverse robust controller (7) is formed by combining an internal model controller (6) and a fuzzy neural network generalized inverse (4); the internal model controller (6) is composed of a speed internal model controller (61) and a current internal model controller (62) which are connected in parallel, the speed internal model controller (61) is composed of a speed internal model (611) and a speed controller (612), and the current internal model controller (62) is composed of a current internal model (621) and a current controller (622) which are connected; the fuzzy neural network generalized inverse system (4) and the composite controlled object (3) are connected in series to form a generalized pseudo-linear system (5), and the generalized pseudo-linear system (5) is equivalent to 1 speed sub-linear system (51) and 1 current sub-linear system (52); the generalized inverse fuzzy neural network (4) consists of a five-layer fuzzy neural network (41) with 5 input nodes and 2 output nodes, two linear transfer functions and 1 integrator; the composite controlled object (3) comprises a current speed detection and calculation module (31) and an extended inverter control part (32) for driving the PMSM (1) in a connected mode, the extended inverter control part (32) is formed by connecting an inverse Park conversion and a voltage source type inverter in an SVPWM debugging mode, the current speed detection and calculation module (31) comprises a current speed calculation part, a Park conversion, a Clarke conversion and a photoelectric encoder (2) in a connected mode, and the Clarke conversion and photoelectric encoder (2) is connected with the PMSM (1).
2. A construction method of a fuzzy neural network generalized inverse robust controller of a permanent magnet synchronous motor is characterized by sequentially comprising the following steps:
1) clarke transformation, Park transformation and a third-order model are equivalent to form a PMSM (1), and the PMSM (1) forms an integrally-formed composite controlled object (3) through a current speed detection and calculation module (31) and an extended inverter control part (32);
2) the method comprises the steps that 2 linear transfer functions, 1 integrator and a fuzzy neural network (41) with determined parameters and weight coefficients are connected in series to form a fuzzy neural network generalized inverse (4), the fuzzy neural network generalized inverse (4) and a composite controlled object (3) are connected in series to form a generalized pseudo-linear system (5), and the generalized pseudo-linear system (5) linearizes and decouples the PMSM (1) and enables the PMSM to be equivalent to 1 second-order pseudo-linear speed subsystem (51) and 1 first-order pseudo-linear current subsystem (52);
3) and respectively introducing a second-order velocity pseudo-linear subsystem (51) and a first-order current pseudo-linear subsystem (52) into an internal model control method to construct an internal model controller (6), combining the internal model controller (6) with a generalized pseudo-linear system (5) to form a fuzzy neural network generalized inverse robust controller (7), and controlling a composite controlled object (3).
3. The method of construction of claim 2 wherein:
in the step 1), the current obtained by Clarke conversion of two-phase stator current of the PMSM (1) and Park conversion and the current, rotor angular speed and angular displacement output after the rotation speed detected by the photoelectric encoder (2) is calculated by a current speed calculating part are used as the output of a current speed detecting and calculating module (31); the input of the composite controlled object (3) is the stator voltage under a d-q coordinate system, and the output is the rotor angular velocity and the two-phase stator current;
in the step 2), 2 input quantities of the generalized inverse (4) of the fuzzy neural network are respectively the rotor angular velocity, the two-phase stator current signals and the linear synthesis quantity of each order derivative thereof, and 2 output quantities are respectively the input of the composite controlled object (3); the method for determining the parameters and the weight coefficient values of the fuzzy neural network (41) comprises the following steps: phi step excitation signal usd，usqRespectively adding the signals to 2 input ends of a composite controlled object (3), and acquiring the rotor angular speed omega of the PMSM (1) in a sampling period of 5msrAnd current isA，isBObtaining the required data through a current speed detection and calculation module (31)
And storing; ② data signal to be storedRespectively off-line obtaining first and second derivatives of speed
First derivative of sum current
Forming a training sample set of a fuzzy neural network (41); thirdly, the fuzzy neural network (41) is trained off line by using a genetic algorithm, a global approximate solution is obtained by roughly adjusting parameters of membership functions of the fuzzy neural network and output initial weights of the membership functions, all parameters and weight coefficients of the fuzzy neural network (41) are roughly determined, and then an optimal gradient method is adopted by error back propagation of driving variables and variable learning rates during specific operationRefining and adjusting parameters of the fuzzy neural network (41) to keep the output mean square error precision of the fuzzy neural network (41) within 0.0005;
in the step 3), the input of the 1 second-order velocity pseudo linear subsystem (51) and the input of the 1 first-order current pseudo linear subsystem (52) are two input quantities of the generalized inverse (4) of the fuzzy neural network respectively, and the output is the current output by the current velocity detection and calculation module (31) and the rotor angular velocity respectively; the generalized inverse robust controller (7) of the fuzzy neural network adopts dSPACE to realize to control the compound controlled object (3).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010102094452A CN101917150B (en) | 2010-06-24 | 2010-06-24 | Robust controller of permanent magnet synchronous motor based on fuzzy-neural network generalized inverse and construction method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010102094452A CN101917150B (en) | 2010-06-24 | 2010-06-24 | Robust controller of permanent magnet synchronous motor based on fuzzy-neural network generalized inverse and construction method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101917150A true CN101917150A (en) | 2010-12-15 |
| CN101917150B CN101917150B (en) | 2012-06-20 |
Family
ID=43324568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010102094452A Active CN101917150B (en) | 2010-06-24 | 2010-06-24 | Robust controller of permanent magnet synchronous motor based on fuzzy-neural network generalized inverse and construction method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101917150B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102437816A (en) * | 2011-10-25 | 2012-05-02 | 武汉鑫通科创科技发展有限公司 | Adaptive motor motion control apparatus based on neural network |
| CN103023398A (en) * | 2012-11-19 | 2013-04-03 | 西安理工大学 | Internal model control method of permanent magnet synchronous motor |
| CN103259479A (en) * | 2013-05-28 | 2013-08-21 | 江苏大学 | Method for observing left inverse state of neural network of permanent magnet synchronous motor |
| CN103345159A (en) * | 2013-07-03 | 2013-10-09 | 江苏大学 | Hybrid electric vehicle BSG system control method based on neural network self-adaptation inversion |
| CN104142626A (en) * | 2014-04-22 | 2014-11-12 | 广东工业大学 | Ship dynamic positioning control method based on inverse system and internal model control |
| CN104155877A (en) * | 2014-08-19 | 2014-11-19 | 江苏科技大学 | Brushless DC motor fuzzy control system based on genetic algorithm and control method thereof |
| CN104184379A (en) * | 2014-08-11 | 2014-12-03 | 南京理工大学 | Self-regulating error symbol integration robust control method for direct-drive motor system |
| CN104852639A (en) * | 2015-05-26 | 2015-08-19 | 江南大学 | Parameter self-tuning speed controller of permanent magnet synchronous motor based on neural network |
| US9390368B2 (en) | 2013-10-21 | 2016-07-12 | International Business Machines Corporation | Coupling parallel event-driven computation with serial computation |
| CN106130431A (en) * | 2016-07-21 | 2016-11-16 | 宿迁学院 | A kind of linear electric motors RBF neural generalized inverse internal model control method |
| CN106249599A (en) * | 2016-09-28 | 2016-12-21 | 河南理工大学 | A kind of network control system fault detection method based on neural network prediction |
| CN106681487A (en) * | 2015-11-05 | 2017-05-17 | 三星电子株式会社 | Walking assistance apparatus and method of controlling same |
| CN106849793A (en) * | 2017-03-01 | 2017-06-13 | 西安交通大学 | A kind of Over Electric Motor with PMSM fuzzy Neural Network Control System |
| CN106934174A (en) * | 2017-03-27 | 2017-07-07 | 上海海事大学 | A kind of modeling of Electrical Propulsion Ship experiment porch and method for analyzing stability |
| CN107490760A (en) * | 2017-08-22 | 2017-12-19 | 西安工程大学 | The circuit breaker failure diagnostic method of fuzzy neural network is improved based on genetic algorithm |
| CN109324503A (en) * | 2018-08-28 | 2019-02-12 | 南京理工大学 | Multilayer neural network electric system control method based on robust integral |
| CN109861618A (en) * | 2019-01-11 | 2019-06-07 | 江苏大学 | The building method of the anti-interference composite controller of Hybrid Vehicle BSG alternating current generator |
| CN111948946A (en) * | 2020-08-24 | 2020-11-17 | 淮阴工学院 | Robust evaluation inversion control system based on HJI theory and design method thereof |
| CN112019111A (en) * | 2020-08-27 | 2020-12-01 | 青岛大学 | State constraint-based fuzzy self-adaptive control method for random system of permanent magnet synchronous motor |
| CN112936270A (en) * | 2021-02-04 | 2021-06-11 | 合肥工业大学 | Mechanical arm internal model control method based on neural network |
| CN113067506A (en) * | 2021-03-09 | 2021-07-02 | 中国地质大学（武汉） | Permanent magnet synchronous motor periodic disturbance suppression method based on inner model equivalent input interference |
| CN113093546A (en) * | 2021-04-02 | 2021-07-09 | 中国科学院光电技术研究所 | Design method of second-order fuzzy-dynamic high-profile controller for photoelectric tracking system |
| CN113574795A (en) * | 2019-03-19 | 2021-10-29 | 松下知识产权经营株式会社 | Motor control method, method for changing control model of motor, motor control system, system for changing control model of motor, and program for changing control model of motor |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1431769A (en) * | 2003-02-20 | 2003-07-23 | 东南大学 | Neural network reversal control frequency converter of induction motor and structure method |
| CN101227160A (en) * | 2007-11-30 | 2008-07-23 | 江苏大学 | Neural network generalized inverse permanent magnetism synchronous machine decoupling controller structure method without bearing |
| CN101299580A (en) * | 2008-03-10 | 2008-11-05 | 江苏大学 | Cooperative controller for two-motor vector control frequency control system and construction method thereof |
| CN101299581A (en) * | 2008-03-10 | 2008-11-05 | 江苏大学 | Neural network generalized inverse coordination control frequency transformer for two induction machines and construction method thereof |
| CN101630940A (en) * | 2009-08-12 | 2010-01-20 | 江苏大学 | Fuzzy neural network inverse robust controller of induction motor speed regulation system and construction method |
| CN101630936A (en) * | 2009-08-12 | 2010-01-20 | 江苏大学 | Neural network inverse controller of brushless DC motor and construction method thereof |
| CN101741297A (en) * | 2009-12-30 | 2010-06-16 | 南京信息职业技术学院 | Radial position fuzzy compensation inverse control method and device for bearingless synchronous reluctance motor |
-
2010
- 2010-06-24 CN CN2010102094452A patent/CN101917150B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1431769A (en) * | 2003-02-20 | 2003-07-23 | 东南大学 | Neural network reversal control frequency converter of induction motor and structure method |
| CN101227160A (en) * | 2007-11-30 | 2008-07-23 | 江苏大学 | Neural network generalized inverse permanent magnetism synchronous machine decoupling controller structure method without bearing |
| CN101299580A (en) * | 2008-03-10 | 2008-11-05 | 江苏大学 | Cooperative controller for two-motor vector control frequency control system and construction method thereof |
| CN101299581A (en) * | 2008-03-10 | 2008-11-05 | 江苏大学 | Neural network generalized inverse coordination control frequency transformer for two induction machines and construction method thereof |
| CN101630940A (en) * | 2009-08-12 | 2010-01-20 | 江苏大学 | Fuzzy neural network inverse robust controller of induction motor speed regulation system and construction method |
| CN101630936A (en) * | 2009-08-12 | 2010-01-20 | 江苏大学 | Neural network inverse controller of brushless DC motor and construction method thereof |
| CN101741297A (en) * | 2009-12-30 | 2010-06-16 | 南京信息职业技术学院 | Radial position fuzzy compensation inverse control method and device for bearingless synchronous reluctance motor |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102437816B (en) * | 2011-10-25 | 2014-05-07 | 武汉鑫通科创科技发展有限公司 | Adaptive motor motion control apparatus based on neural network |
| CN102437816A (en) * | 2011-10-25 | 2012-05-02 | 武汉鑫通科创科技发展有限公司 | Adaptive motor motion control apparatus based on neural network |
| CN103023398A (en) * | 2012-11-19 | 2013-04-03 | 西安理工大学 | Internal model control method of permanent magnet synchronous motor |
| CN103023398B (en) * | 2012-11-19 | 2015-01-21 | 西安理工大学 | Internal model control method of permanent magnet synchronous motor |
| CN103259479B (en) * | 2013-05-28 | 2016-08-10 | 江苏大学 | A kind of permanent magnet synchronous electric machine neural network left inverse state observation method |
| CN103259479A (en) * | 2013-05-28 | 2013-08-21 | 江苏大学 | Method for observing left inverse state of neural network of permanent magnet synchronous motor |
| CN103345159A (en) * | 2013-07-03 | 2013-10-09 | 江苏大学 | Hybrid electric vehicle BSG system control method based on neural network self-adaptation inversion |
| US10678741B2 (en) | 2013-10-21 | 2020-06-09 | International Business Machines Corporation | Coupling parallel event-driven computation with serial computation |
| US9390368B2 (en) | 2013-10-21 | 2016-07-12 | International Business Machines Corporation | Coupling parallel event-driven computation with serial computation |
| CN104142626A (en) * | 2014-04-22 | 2014-11-12 | 广东工业大学 | Ship dynamic positioning control method based on inverse system and internal model control |
| CN104184379A (en) * | 2014-08-11 | 2014-12-03 | 南京理工大学 | Self-regulating error symbol integration robust control method for direct-drive motor system |
| CN104155877A (en) * | 2014-08-19 | 2014-11-19 | 江苏科技大学 | Brushless DC motor fuzzy control system based on genetic algorithm and control method thereof |
| CN104852639A (en) * | 2015-05-26 | 2015-08-19 | 江南大学 | Parameter self-tuning speed controller of permanent magnet synchronous motor based on neural network |
| CN106681487B (en) * | 2015-11-05 | 2021-05-04 | 三星电子株式会社 | Walking assistance apparatus and method of controlling walking assistance apparatus |
| CN106681487A (en) * | 2015-11-05 | 2017-05-17 | 三星电子株式会社 | Walking assistance apparatus and method of controlling same |
| CN106130431B (en) * | 2016-07-21 | 2018-09-28 | 宿迁学院 | A kind of linear motor RBF neural generalized inverse internal model control method |
| CN106130431A (en) * | 2016-07-21 | 2016-11-16 | 宿迁学院 | A kind of linear electric motors RBF neural generalized inverse internal model control method |
| CN106249599B (en) * | 2016-09-28 | 2020-01-10 | 河南理工大学 | Neural network prediction-based networked control system fault detection method |
| CN106249599A (en) * | 2016-09-28 | 2016-12-21 | 河南理工大学 | A kind of network control system fault detection method based on neural network prediction |
| CN106849793A (en) * | 2017-03-01 | 2017-06-13 | 西安交通大学 | A kind of Over Electric Motor with PMSM fuzzy Neural Network Control System |
| CN106849793B (en) * | 2017-03-01 | 2019-03-01 | 西安交通大学 | A kind of Over Electric Motor with PMSM fuzzy Neural Network Control System |
| CN106934174A (en) * | 2017-03-27 | 2017-07-07 | 上海海事大学 | A kind of modeling of Electrical Propulsion Ship experiment porch and method for analyzing stability |
| CN106934174B (en) * | 2017-03-27 | 2020-06-05 | 上海海事大学 | Modeling and stability analysis method for electric propulsion ship experiment platform |
| CN107490760A (en) * | 2017-08-22 | 2017-12-19 | 西安工程大学 | The circuit breaker failure diagnostic method of fuzzy neural network is improved based on genetic algorithm |
| CN109324503A (en) * | 2018-08-28 | 2019-02-12 | 南京理工大学 | Multilayer neural network electric system control method based on robust integral |
| CN109861618B (en) * | 2019-01-11 | 2020-11-20 | 江苏大学 | Construction method of anti-interference composite controller of BSG alternating current motor for hybrid electric vehicle |
| CN109861618A (en) * | 2019-01-11 | 2019-06-07 | 江苏大学 | The building method of the anti-interference composite controller of Hybrid Vehicle BSG alternating current generator |
| CN113574795A (en) * | 2019-03-19 | 2021-10-29 | 松下知识产权经营株式会社 | Motor control method, method for changing control model of motor, motor control system, system for changing control model of motor, and program for changing control model of motor |
| CN111948946A (en) * | 2020-08-24 | 2020-11-17 | 淮阴工学院 | Robust evaluation inversion control system based on HJI theory and design method thereof |
| CN111948946B (en) * | 2020-08-24 | 2022-05-17 | 淮阴工学院 | Robust evaluation inversion control system based on HJI theory and design method thereof |
| CN112019111A (en) * | 2020-08-27 | 2020-12-01 | 青岛大学 | State constraint-based fuzzy self-adaptive control method for random system of permanent magnet synchronous motor |
| CN112936270A (en) * | 2021-02-04 | 2021-06-11 | 合肥工业大学 | Mechanical arm internal model control method based on neural network |
| CN112936270B (en) * | 2021-02-04 | 2022-05-03 | 合肥工业大学 | Mechanical arm internal model control method based on neural network |
| CN113067506A (en) * | 2021-03-09 | 2021-07-02 | 中国地质大学（武汉） | Permanent magnet synchronous motor periodic disturbance suppression method based on inner model equivalent input interference |
| CN113093546A (en) * | 2021-04-02 | 2021-07-09 | 中国科学院光电技术研究所 | Design method of second-order fuzzy-dynamic high-profile controller for photoelectric tracking system |
| CN113093546B (en) * | 2021-04-02 | 2022-11-11 | 中国科学院光电技术研究所 | Design method of second-order fuzzy-dynamic high-profile controller for photoelectric tracking system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101917150B (en) | 2012-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101917150B (en) | Robust controller of permanent magnet synchronous motor based on fuzzy-neural network generalized inverse and construction method thereof | |
| Emhemed et al. | Modelling and simulation for industrial DC motor using intelligent control | |
| Premkumar et al. | Speed control of Brushless DC motor using bat algorithm optimized Adaptive Neuro-Fuzzy Inference System | |
| CN108777556B (en) | Model-free adaptive robust decoupling control method for two-motor speed regulation system | |
| CN105375848B (en) | A kind of permanent magnet synchronous motor Adaptive Identification control method and its control system | |
| Yan et al. | Torque estimation and control of PMSM based on deep learning | |
| Lftisi et al. | Artificial neural network based speed controller for induction motors | |
| CN103944481A (en) | AC asynchronous motor vector control system model parameter online modifying method | |
| Chaouch et al. | Optimized torque control via backstepping using genetic algorithm of induction motor | |
| Rayyam et al. | A new metaheuristic unscented Kalman filter for state vector estimation of the induction motor based on Ant Lion optimizer | |
| CN111948947A (en) | Nonlinear current simulation and robust control method of motor simulator | |
| Wai | Hybrid control for speed sensorless induction motor drive | |
| Djelamda et al. | Field-oriented control based on adaptive neuro-fuzzy inference system for PMSM dedicated to electric vehicle | |
| Wang et al. | Lion swarm optimisation‐based tuning method for generalised predictive fractional‐order PI to control the speed of brushless direct current motor | |
| Rigatos et al. | Derivative‐free nonlinear Kalman filtering for PMSG sensorless control | |
| Liu et al. | Practical discontinuous tracking control for a permanent magnet synchronous motor | |
| Ting et al. | Novel mingled reformed recurrent Hermite polynomial neural network control system applied in continuously variable transmission system | |
| Yang et al. | An improved neural networks-based vector control approach for permanent magnet linear synchronous motor | |
| CN114094896A (en) | Self-configuration T-S type fuzzy neural network control method of permanent magnet synchronous motor | |
| CN117097220B (en) | EMPC current loop control method and system applied to electric forklift induction motor | |
| Zerikat et al. | Fuzzy-neural networks controller-based adapatation mechanism for MRAS sensorless induction motor drives | |
| Gencer et al. | DSP based fuzzy-neural speed tracking control of brushless DC motor | |
| Feng et al. | Mechanical parameter recognition of permanent magnet synchronous motor based on RBFNN algorithm | |
| Lin et al. | A PID neural network control for permanent magnet synchronous motor servo system | |
| Hsu et al. | Parameter Space Design of Speed Controller for BLDC Motor Using SIWPSO-RBFNN Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211220 Address after: 212200 No. 1, pilot Road, Yangzhong high tech Industrial Development Zone, Zhenjiang City, Jiangsu Province Patentee after: DAHANG YOUNENG ELECTRICAL CO.,LTD. Address before: 212013 No. 301, Xuefu Road, Zhenjiang, Jiangsu Patentee before: JIANGSU University |