A Position Control Method, Device, Equipment and Medium for a Planar Motor

Abstract

The present invention discloses a position control method, device, equipment and medium for a planar motor. Among them, the method includes: determining a position prediction model according to the discrete state space model of the target planar motor and the position information at the current moment, and determining a speed prediction model according to the position prediction model and the preset discrete sampling time; determining a position control optimization model according to the reference position information, position prediction model and speed prediction model of the target planar motor; converting the position control optimization model into a quadratic programming model, and determining the output equation and state equation of the dual neural network according to the dual model of the quadratic programming model; solving the position control optimization model accordingly to obtain the target control thrust, and performing position control on the target planar motor according to the target control thrust. This solution can use the dual neural network to quickly solve the hard constraint optimization problem in the motor operation process and achieve high-precision position control of the planar motor.

Description

Technical Field

[0001] The present invention relates to the technical field of motor control, and particularly relates to a position control method, device, equipment and medium for a planar motor. Background Art

[0002] A planar motor is a motor that can directly convert electromagnetic energy into planar motion. Due to its high-precision positioning ability, it is widely used in industrial automation, medical equipment, aerospace and other fields. The model predictive control method has the ability to handle system nonlinearity, multi-input multi-output, and constraint problems. If the model predictive control method is applied to the position control of a planar motor, it is expected to further improve the position control accuracy of the planar motor.

[0003] The rapid solution of the hard constraint optimization problem is a research hotspot and difficulty of the model predictive control method. The existing solution methods for the hard constraint optimization problem in the commonly used model predictive control have disadvantages such as weak constraint ability, long solution time, and high algorithm complexity. Therefore, when applying the model predictive control method to the planar motor position system, there are problems such as inability to strictly constrain the control input, complex algorithm, poor real-time performance, and poor control effect. Summary of the Invention

[0004] The present invention provides a position control method, device, equipment and medium for a planar motor. The dual neural network is applied to the position control of the planar motor, and the created dual neural network is used to quickly solve the hard constraint optimization problem in the real-time operation process of the motor position system. During the solution process, the motor position error and speed error are considered simultaneously, so that the planar motor tracks the reference position at the speed corresponding to the reference position information, and high-precision and efficient control of the planar motor position can be achieved on the premise of ensuring the safe operation of the planar motor.

[0005] According to one aspect of the present invention, a position control method for a planar motor is provided. The method includes:

[0006] Determine the position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the position information at the current moment, and determine the speed prediction model according to the position prediction model and the preset discrete sampling time; wherein, the state space model is used to describe the relationship between the position of the motor and the control thrust, and the control thrust is used to control the movement of the motor;

[0007] Determine the position control optimization model of the target planar motor according to the reference position information of the target planar motor, the position prediction model, and the speed prediction model; wherein, the position control optimization model includes an objective cost function and a control thrust constraint condition, the objective cost function is established based on the control thrust, position error, and speed error of the target planar motor, and the control thrust constraint condition is determined based on the current operating characteristics of the target planar motor;

[0008] Convert the position control optimization model into a quadratic programming model, and determine the output equation and state equation of the dual neural network according to the dual model of the quadratic programming model; wherein, the state equation is used to describe the relationship between the optimization variables at adjacent times in the dual model, and the output equation is used to describe the relationship between the control thrust and the optimization variables;

[0009] Solve the position control optimization model based on the output equation and state equation of the dual neural network to obtain the target control thrust, and perform position control on the target planar motor according to the target control thrust.

[0010] According to another aspect of the present invention, there is provided a position control device for a planar motor, the device includes:

[0011] A prediction model determination module, configured to determine the position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the current position information, and determine the speed prediction model according to the position prediction model and the preset discrete sampling time; wherein, the state space model is used to describe the relationship between the position of the motor and the control thrust, and the control thrust is used to control the movement of the motor;

[0012] A position control optimization model determination module, configured to determine the position control optimization model of the target planar motor according to the reference position information of the target planar motor, the position prediction model, and the speed prediction model; wherein, the position control optimization model includes an objective cost function and a control thrust constraint condition, the objective cost function is established based on the control thrust, position error, and speed error of the target planar motor, and the control thrust constraint condition is determined based on the current operating characteristics of the target planar motor;

[0013] A dual neural network determination module, configured to convert the position control optimization model into a quadratic programming model, and determine the output equation and state equation of the dual neural network according to the dual model of the quadratic programming model; wherein, the state equation is used to describe the relationship between the optimization variables at adjacent times in the dual model, and the output equation is used to describe the relationship between the control thrust and the optimization variables;

[0014] A motor position control module is configured to solve the position control optimization model based on the output equation and the state equation of the dual neural network to obtain a target control thrust, and perform position control on the target planar motor according to the target control thrust.

[0015] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0016] At least one processor; and,

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the position control method of the planar motor according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the position control method of the planar motor according to any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention determines the position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the position information at the current moment, and determines the speed prediction model according to the position prediction model and the preset discrete sampling time; wherein, the state space model is used to describe the relationship between the position of the motor and the control thrust, and the control thrust is used to control the movement of the motor; determine the position control optimization model of the target planar motor according to the reference position information, position prediction model and speed prediction model of the target planar motor; wherein, the position control optimization model includes an objective cost function and a control thrust constraint condition, and the objective cost function is established based on the control thrust, position error and speed error of the target planar motor, and the control thrust constraint condition is determined based on the current working characteristics of the target planar motor; convert the position control optimization model into a quadratic programming model, and determine the output equation and state equation of the dual neural network according to the dual model of the quadratic programming model; wherein, the state equation is used to describe the relationship between the optimization variables at adjacent moments in the dual model, and the output equation is used to describe the relationship between the control thrust and the optimization variables; solve the position control optimization model based on the output equation and state equation of the dual neural network to obtain the target control thrust, and perform position control on the target planar motor according to the target control thrust. In this technical solution, the dual neural network is applied to the position control of the planar motor, and the created dual neural network is used to quickly solve the hard-constrained optimization problem in the real-time operation process of the motor position system. In addition, an objective cost function of the hard-constrained optimization problem is established based on the position error and speed error of the planar motor. When solving the hard-constrained optimization problem, the position error and speed error are considered at the same time, so that the planar motor can track the reference position at the speed corresponding to the reference position information, and can achieve high-precision and efficient control of the position of the planar motor on the premise of ensuring the safe operation of the planar motor.

[0021] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0023] Figure 1 is a flowchart of a method for controlling the position of a planar motor according to Embodiment 1 of the present invention;

[0024] Figure 2It is a flowchart of a position control method for a planar motor according to Embodiment 2 of the present invention;

[0025] Figure 3 It is a schematic diagram of position control for a planar switched reluctance motor according to Embodiment 2 of the present invention;

[0026] Figure 4 It is a schematic structural diagram of a position control device for a planar motor according to Embodiment 3 of the present invention;

[0027] Figure 5 It is a schematic structural diagram of an electronic device for implementing the position control method of a planar motor according to an embodiment of the present invention. Detailed implementation manners

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0029] It should be noted that the terms "first", "second", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0030] Embodiment 1

[0031] Figure 1 It is a flowchart of a position control method for a planar motor provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of high-precision and efficient control of the position of a planar motor. This method can be executed by a position control device of the planar motor. The position control device of the planar motor can be implemented in the form of hardware and / or software, and the position control device of the planar motor can be configured in an electronic device with data processing capabilities. As Figure 1 shown, the method includes:

[0032] S110. Determine the position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the position information at the current moment, and determine the speed prediction model according to the position prediction model and the preset discrete sampling time.

[0033] Among them, the target planar motor may refer to the planar motor that needs to perform position control. Exemplary planar motors may include variable reluctance planar motors, permanent magnet synchronous planar motors, and stepper planar motors, etc. The state space model is used to describe the relationship between the position of the motor and the control thrust, and the control thrust is used to control the movement of the motor. The position prediction model can be used to predict the position of the planar motor. The speed prediction model can be used to predict the speed of the planar motor. The preset discrete sampling time may refer to the sampling period corresponding to the discrete state space model preset according to actual needs, which is the same as the outer loop control period of the target planar motor.

[0034] In this embodiment, optionally, before determining the position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the position information at the current moment, it further includes: determining the continuous state space model of the target planar motor; discretizing the continuous state space model based on the preset discrete sampling time to obtain the discrete state space model.

[0035] Specifically, the continuous state space model can be expressed as formula (1): . Among them, is the continuous state variable, is the derivative of, is the continuous input control variable, is the continuous output variable, is the continuous motor system matrix, is the continuous input matrix, is the output matrix. It should be noted that the input control variable is the control thrust, the state variables include the motor position and the motor speed, and the output variable is the motor position. Since this solution focuses on motor position control, the output matrix can be set to act on the state variables so that the output variable is the motor position. Further, if motor speed control is to be achieved, the output matrix can also be set to act on the state variables so that the output variable is the motor speed.

[0036] In this embodiment, the discrete Euler method can be used to discretize formula (1) to obtain the discrete state space model of the planar motor, which can be specifically expressed as formula (2): . Among them, is the discrete state variable at the k + 1 moment, is the discrete input control variable, is the discrete output variable, is the discrete motor system matrix, is a discrete input matrix, and represent the current sampling time and the next sampling time respectively. Among them, is a two-dimensional matrix containing the motor position and the motor speed.

[0037] After determining the discrete state space model of the target plane motor, the position prediction model of the target plane motor can be determined according to the discrete state space model and the position information at the current moment. Specifically, within a finite time domain, assuming the prediction time domain has a prediction step size of , and the control time domain has a control step size of , where , then the position prediction model of the target plane motor can be expressed as the following formula (3): . It should be noted that the motor position in

[0038] is the position information at the current moment. Among them:

[0039] ;

[0040] ;

[0041] .

[0042] Among them, is the position prediction model of the target plane motor, used for predicting the position information of the target plane motor; is the control quantity matrix from k to (k + m - 1), equivalent to the control variable input into the model.

[0043] After determining the position prediction model of the target plane motor, the speed prediction model can be determined according to the difference between the position prediction models at adjacent discrete sampling times and the preset discrete sampling time. Specifically, the speed prediction model of the target plane motor can be expressed as the following formula (4): . Among them:

[0044] ;

[0045] ;

[0046] ;

[0047] Among them, is the speed prediction model of the target plane motor, used for predicting the speed of the target plane motor; is the identity matrix; represents dividing all elements of the matrix by a preset discrete sampling time .

[0048] S120, determine the position control optimization model of the target planar motor according to the reference position information, position prediction model and speed prediction model of the target planar motor; wherein, the position control optimization model includes an objective cost function and a control thrust constraint condition, and the objective cost function is established based on the control thrust, position error and speed error of the target planar motor, and the control thrust constraint condition is determined based on the current operating characteristics of the target planar motor.

[0049] Among them, the reference position information can be used to describe which position the motor wants to run to, and can be flexibly set according to actual needs. Exemplarily, the reference position information can be used to describe the motor operation trajectory in the form of sine or cosine. The position error can be used to represent the difference between the reference position information and the position prediction model, and the speed error can be used to represent the difference between the reference speed information and the speed prediction model, wherein the reference speed information can be determined based on the ratio of the difference between the reference position information at adjacent discrete sampling moments to the preset discrete sampling time. The position control optimization model includes an objective cost function and a control thrust constraint condition.

[0050] Among them, the objective cost function can be used to describe the difference between the reference position information and the predicted position information. The control thrust constraint condition can be used to describe the normal operating range of the control thrust, for example, it can be characterized by the upper limit value and the lower limit value of the control thrust. Among them, the control thrust constraint condition is determined based on the current operating characteristics of the target planar motor, and the current operating characteristics can be used to describe the normal operating range of the current. It should be noted that there is a certain conversion relationship between the current and the control thrust. Therefore, based on the known normal operating range of the current, the normal operating range of the control thrust can be obtained correspondingly using the conversion relationship between the two, and the normal operating range of the control thrust can be used as the control thrust constraint condition, so as to ensure the safe operation of the motor.

[0051] In this embodiment, after determining the position prediction model and the speed prediction model, the position control optimization model of the target planar motor can be determined according to the reference position information, the position prediction model, and the speed prediction model of the target planar motor. Optionally, determining the position control optimization model of the target planar motor according to the reference position information, the position prediction model, and the speed prediction model of the target planar motor includes: determining reference speed information according to the reference position information and the preset discrete sampling time; determining a position error matrix according to the difference between the reference position information and the position prediction model, and determining a first parameter matrix according to the product of the first weight matrix and the position error matrix; determining a second parameter matrix according to the product of the second weight matrix and the control thrust matrix; determining a speed error matrix according to the difference between the reference speed information and the speed prediction model, and determining a third parameter matrix according to the product of the third weight matrix and the speed error matrix; determining a target cost function according to the first parameter matrix, the second parameter matrix, and the third parameter matrix; determining a control thrust constraint condition according to the current operating range of the target planar motor and the current-control thrust conversion relationship; and determining the position control optimization model of the target planar motor according to the target cost function and the control thrust constraint condition.

[0052] Among them, the first weight matrix can be used to represent the weight of the position error matrix, the second weight matrix can be used to represent the weight of the control thrust matrix, and the third weight matrix can be used to represent the weight of the speed error matrix. The current-control thrust conversion relationship can be used to describe the mapping relationship between the current and the control thrust of the target planar motor.

[0053] Exemplarily, the position control optimization model can be expressed as the following formula (5):

[0054] .

[0055] Among them, ;

[0056] ;

[0057] , , .

[0058] Among them, is the target cost function, is the reference position information, is the reference speed information, is the position error matrix, is the speed error matrix, is the control thrust matrix, is the first weight matrix, is the first parameter matrix, is the second weight matrix, is the second parameter matrix, is the third weight matrix, is the third parameter matrix, and are the minimum and maximum values of the control thrust respectively, is the control thrust constraint condition (i.e., hard constraint). Therefore, the position control optimization model can be regarded as an optimization problem with hard constraints.

[0059] S130. Convert the position control optimization model into a quadratic programming model, and determine the output equation and state equation of the dual neural network according to the dual model of the quadratic programming model.

[0060] Among them, the dual neural network can refer to a structure that can solve the optimal control quantity for the position control optimization model. The state equation is used to describe the relationship between the optimization variables at adjacent moments in the dual model, and the output equation is used to describe the relationship between the control thrust and the optimization variables.

[0061] In this embodiment, formula (5) can be converted into a quadratic programming problem to obtain the corresponding quadratic programming model, which can be specifically expressed as formula (6) as follows: . Among them, , , , , , is the identity matrix, . Further, the dual model of formula (6) can be obtained, which is specifically expressed as formula (7): . Among them, and are the optimization variables of the dual problem. Let . According to the KKT (Karush-Kuhn-Tucker) conditions of the convex optimization problem, formula (6) and formula (7) have the same solution as the following system of equations (8), and this equation (8) can be specifically expressed as: . According to the projection formula, equation (8) can be equivalently expressed as equation (9): . Among them, is a piecewise linear function, defined as: ; ; is the i-th element of the column vector, is the i-th element of the column vector,

[0062] Because, is an invertible matrix. From the first equation in Equation (9), the output equation of the dual neural network can be obtained, which is specifically expressed as Equation (10): . Substituting Equation (10) into the second equation in Equation (9) gives Equation (11): . Based on Equation (11), the state equation of the dual neural network under continuous time can be established, which can be specifically expressed as Equation (12): . Among them, is a parameter regarding the convergence rate of the dual neural network.

[0063] It should be noted that the dual neural network algorithm can be implemented using digital circuits, and the construction of the dual neural network and the adjustment of network parameters can be achieved through software programming. It is easy to implement and is more suitable for quickly solving the position control optimization model of planar motors.

[0064] Furthermore, according to the Euler method, the differential term in Equation (12) can be expressed as Equation (13): . Among them, is the time for the dual neural network to complete one update of the optimization variable , is the sampling time of the discrete dual neural network.

[0065] Substituting Equation (13) into Equation (12), the state equation of the discrete-time dual neural network can be obtained, which is specifically expressed as Equation (14): . Among them, is a scaling parameter that determines the convergence rate of the discrete-time dual neural network. At the same time, the output equation of the discrete-time dual neural network can be obtained, which is expressed as Equation (15): .

[0066] S140. Based on the output equation and state equation of the dual neural network, solve the position control optimization model to obtain the target control thrust, and perform position control on the target planar motor according to the target control thrust.

[0067] In this embodiment, after determining the output equation and state equation of the dual neural network, the position control optimization model can be solved based on the output equation and state equation of the dual neural network to obtain the target control thrust. Optionally, solving the position control optimization model based on the output equation and state equation of the dual neural network to obtain the target control thrust includes: solving the position control optimization model according to the state equation of the dual neural network to obtain the target optimization variable value; determining the target control thrust according to the output equation of the dual neural network and the target optimization variable value.

[0068] Specifically, the target optimization variable value , and then substitute into formula (15) to obtain the optimal control quantity . Then, use the first element of the optimal control quantity as the target control thrust at the current moment, that is . Repeat the above steps at moment, and the target control thrust at moment can be obtained.

[0069] After obtaining the target control thrust, the position control of the target planar motor can be performed according to the target control thrust. Optionally, performing the position control of the target planar motor according to the target control thrust includes: determining the target current corresponding to the target control thrust according to the current-control thrust conversion relationship; inputting the target current into the current driver to obtain the target voltage, and performing the position control of the target planar motor according to the target voltage.

[0070] Among them, the target current includes three-phase currents, and correspondingly, the target voltage includes three-phase voltages. Exemplarily, the current-control thrust conversion relationship may include a force-current conversion model and a force distribution function. Specifically, the target control thrust can be converted into three-phase currents as the target current according to the force-current conversion model and the force distribution function, and then the target current is input into the current driver, and the corresponding three-phase voltages are obtained as the target voltages. Furthermore, the target voltages can act on the target planar motor to achieve high-precision position control of the target planar motor through the target voltages.

[0071] The technical solution of the embodiment of the present invention determines the position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the position information at the current moment, and determines the speed prediction model according to the position prediction model and the preset discrete sampling time; wherein, the state space model is used to describe the relationship between the position of the motor and the control thrust, and the control thrust is used to control the movement of the motor; determine the position control optimization model of the target planar motor according to the reference position information, position prediction model and speed prediction model of the target planar motor; wherein, the position control optimization model includes an objective cost function and a control thrust constraint condition, and the objective cost function is established based on the control thrust, position error and speed error of the target planar motor, and the control thrust constraint condition is determined based on the current operating characteristics of the target planar motor; transform the position control optimization model into a quadratic programming model, and determine the output equation and state equation of the dual neural network according to the dual model of the quadratic programming model; wherein, the state equation is used to describe the relationship between the optimization variables at adjacent moments in the dual model, and the output equation is used to describe the relationship between the control thrust and the optimization variables; solve the position control optimization model based on the output equation and state equation of the dual neural network to obtain the target control thrust, and perform position control on the target planar motor according to the target control thrust. In this technical solution, the dual neural network is applied to the position control of the planar motor, and the created dual neural network is used to quickly solve the hard-constrained optimization problem during the real-time operation of the motor position system. In addition, an objective cost function for the hard-constrained optimization problem is established based on the position error and speed error of the planar motor. When solving the hard-constrained optimization problem, both the position error and speed error are considered, so that the planar motor can track the reference position at the speed corresponding to the reference position information, and high-precision and efficient control of the position of the planar motor can be achieved on the premise of ensuring the safe operation of the planar motor.

[0072] Embodiment 2

[0073] Figure 2 It is a flowchart of a position control method for a planar motor provided by Embodiment 2 of the present invention. This embodiment is optimized based on the above embodiment.

[0074] As Figure 2 shown, the method of this embodiment specifically includes the following steps:

[0075] S210, determine the continuous state space model of the target planar motor, and discretize the continuous state space model based on the preset discrete sampling time to obtain the discrete state space model.

[0076] S220, determine the position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the position information at the current moment, and determine the speed prediction model according to the position prediction model and the preset discrete sampling time.

[0077] Among them, the state space model is used to describe the relationship between the position of the motor and the control thrust, and the control thrust is used to control the movement of the motor.

[0078] S230. Determine the reference speed information according to the reference position information and the preset discrete sampling time.

[0079] S240. Determine the position error matrix according to the difference between the reference position information and the position prediction model, and determine the first parameter matrix according to the product of the first weight matrix and the position error matrix.

[0080] S250. Determine the second parameter matrix according to the product of the second weight matrix and the control thrust matrix.

[0081] S260. Determine the speed error matrix according to the difference between the reference speed information and the speed prediction model, and determine the third parameter matrix according to the product of the third weight matrix and the speed error matrix.

[0082] S270. Determine the objective cost function according to the first parameter matrix, the second parameter matrix, and the third parameter matrix.

[0083] S280. Determine the control thrust constraint conditions according to the current operating range of the target planar motor and the current-control thrust conversion relationship.

[0084] S290. Determine the position control optimization model of the target planar motor according to the objective cost function and the control thrust constraint conditions.

[0085] S2100. Convert the position control optimization model into a quadratic programming model, and determine the output equation and the state equation of the dual neural network according to the dual model of the quadratic programming model.

[0086] Among them, the state equation is used to describe the relationship between the optimization variables at adjacent moments in the dual model, and the output equation is used to describe the relationship between the control thrust and the optimization variables.

[0087] S2110. Solve the position control optimization model based on the output equation and the state equation of the dual neural network to obtain the target control thrust, and perform position control on the target planar motor according to the target control thrust.

[0088] Figure 3 This is a schematic diagram of the position control of a planar switched reluctance motor provided in the second embodiment of the present invention. Exemplarily, as Figure 3 shown, taking the X-axis position control of the planar switched reluctance motor as an example, the target control thrust corresponding to the X-axis position of the planar switched reluctance motor can be predicted by a predictive position controller. Among them, in the dual neural network represents a one-cycle delay and can be used to update the state.

[0089] Specifically, first, the current position information of the planar switched reluctance motor is obtained through the X-axis position sensor , and based on the discrete state space model of the planar switched reluctance motor and the current position information a position prediction model is obtained . Then, according to the position prediction model and the preset discrete sampling time, a speed prediction model is determined . Then, according to the reference position information , the reference speed information , the position prediction model and the speed prediction model a position control optimization model with hard constraints is determined , and the dual neural network is used to solve the position control optimization model to obtain the optimal control quantity . The first element of the optimal control quantity is used as the target control thrust at the current moment . Furthermore, according to the force distribution function and the force-current conversion model, the target control thrust is converted into the target current, where the target current includes , and . Then, the target current is input into the current driver to obtain the target voltage, where the target voltage includes , and . Finally, the target voltage acts on the planar switched reluctance motor to control the movement of the motor, thereby obtaining the corresponding predicted position information .

[0090] In the technical solution of the embodiment of the present invention, by applying the dual neural network to the position control of the planar motor, the dual neural network created is used to quickly solve the optimization problem with hard constraints in the real-time operation process of the motor position system. In addition, based on the position error and speed error of the planar motor, an objective cost function of the optimization problem with hard constraints is established, and both the position error and speed error are considered when solving the optimization problem with hard constraints, enabling the planar motor to track the reference position at the speed corresponding to the reference position information, and realizing high-precision and efficient control of the position of the planar motor on the premise of ensuring the safe operation of the planar motor.

[0091] Embodiment III

[0092] Figure 4 FIG. is a schematic structural diagram of a position control device for a planar motor provided in Embodiment III of the present invention. This device can execute the position control method of the planar motor provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. AsFigure 4 As shown, the device includes:

[0093] A prediction model determination module 310, configured to determine a position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the position information at the current moment, and determine a speed prediction model according to the position prediction model and a preset discrete sampling time; wherein, the state space model is used to describe the relationship between the position of the motor and the control thrust, and the control thrust is used to control the movement of the motor;

[0094] A position control optimization model determination module 320, configured to determine a position control optimization model of the target planar motor according to the reference position information, the position prediction model, and the speed prediction model of the target planar motor; wherein, the position control optimization model includes an objective cost function and a control thrust constraint condition, the objective cost function is established based on the control thrust, position error, and speed error of the target planar motor, and the control thrust constraint condition is determined based on the current operating characteristics of the target planar motor;

[0095] A dual neural network determination module 330, configured to transform the position control optimization model into a quadratic programming model, and determine an output equation and a state equation of the dual neural network according to the dual model of the quadratic programming model; wherein, the state equation is used to describe the relationship between the optimization variables at adjacent moments in the dual model, and the output equation is used to describe the relationship between the control thrust and the optimization variables;

[0096] A motor position control module 340, configured to solve the position control optimization model based on the output equation and the state equation of the dual neural network to obtain a target control thrust, and perform position control on the target planar motor according to the target control thrust.

[0097] Optionally, the device further includes: a state space model discretization module, configured to:

[0098] Before determining the position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the position information at the current moment, determine the continuous state space model of the target planar motor;

[0099] Discretize the continuous state space model based on the preset discrete sampling time to obtain a discrete state space model.

[0100] Optionally, the position control optimization model determination module is configured to:

[0101] Determine reference speed information according to the reference position information and the preset discrete sampling time;

[0102] Determine a position error matrix based on the difference between the reference position information and the position prediction model, and determine a first parameter matrix according to the product of the first weight matrix and the position error matrix;

[0103] Determine a second parameter matrix according to the product of the second weight matrix and the control thrust matrix;

[0104] Determine a speed error matrix based on the difference between the reference speed information and the speed prediction model, and determine a third parameter matrix according to the product of the third weight matrix and the speed error matrix;

[0105] Determine a target cost function according to the first parameter matrix, the second parameter matrix, and the third parameter matrix;

[0106] Determine a control thrust constraint condition according to the current operating range of the target planar motor and the current-control thrust conversion relationship;

[0107] Determine a position control optimization model of the target planar motor according to the target cost function and the control thrust constraint condition.

[0108] Optionally, the motor position control module 340 is configured to:

[0109] Solve the position control optimization model according to the state equation of the dual neural network to obtain a target optimization variable value;

[0110] Determine a target control thrust according to the output equation of the dual neural network and the target optimization variable value.

[0111] Optionally, the motor position control module 340 is further configured to:

[0112] Determine a target current corresponding to the target control thrust according to the current-control thrust conversion relationship;

[0113] Input the target current into a current driver to obtain a target voltage, and perform position control on the target planar motor according to the target voltage.

[0114] The position control device of a planar motor provided by an embodiment of the present invention can execute a position control method of a planar motor provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0115] Embodiment IV

[0116] Figure 5The structural schematic diagram of an electronic device 10 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0117] As Figure 5 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0118] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0119] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the position control method of the planar motor.

[0120] In some embodiments, the position control method of the planar motor can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the position control method of the planar motor described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the position control method of the planar motor by any other suitable means (e.g., by means of firmware).

[0121] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a dedicated computer, or other programmable data processing device such that when the computer programs are executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0123] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0124] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0125] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0126] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0127] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0128] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A position control method for a planar motor, characterized in that: The method comprises: Determine a position prediction model of the target planar motor according to a discrete state space model of the target planar motor and the current position information, and determine a speed prediction model according to the position prediction model and a preset discrete sampling time; wherein the state space model is used to describe the relationship between the position of the motor and the control thrust, and the control thrust is used to control the movement of the motor; Determine a position control optimization model of the target planar motor according to the reference position information of the target planar motor, the position prediction model and the speed prediction model; wherein the position control optimization model includes a target cost function and a control thrust constraint condition, the target cost function is established based on the control thrust, position error and speed error of the target planar motor, and the control thrust constraint condition is determined based on the current working characteristics of the target planar motor; The position control optimization model is converted into a quadratic programming model, and the output equation and state equation of the dual neural network are determined according to the dual model of the quadratic programming model; wherein the state equation is used to describe the relationship between the optimization variables at adjacent moments in the dual model, and the output equation is used to describe the relationship between the control thrust and the optimization variables; The position control optimization model is solved based on the output equation and the state equation of the dual neural network to obtain the target control thrust, and the position of the target planar motor is controlled according to the target control thrust.

2. The method according to claim 1, characterized in that Before determining the position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the current position information, the method further includes: Determining a continuous state space model of the target planar motor; The continuous state space model is discretized based on the preset discrete sampling time to obtain a discrete state space model.

3. The method according to claim 1 or 2, characterized in that: Determining a position control optimization model of the target planar motor according to the reference position information of the target planar motor, the position prediction model and the speed prediction model, including: Determine reference speed information according to the reference position information and the preset discrete sampling time; Determine a position error matrix according to the difference between the reference position information and the position prediction model, and determine a first parameter matrix according to the product of a first weight matrix and the position error matrix; Determine a second parameter matrix according to the product of the second weight matrix and the control thrust matrix; Determine a speed error matrix according to the difference between the reference speed information and the speed prediction model, and determine a third parameter matrix according to the product of a third weight matrix and the speed error matrix; Determine a target cost function according to the first parameter matrix, the second parameter matrix and the third parameter matrix; Determining a control thrust constraint condition according to a current operating range of the target planar motor and a current-control thrust conversion relationship; A position control optimization model of the target planar motor is determined according to the target cost function and the control thrust constraint condition.

4. The method according to claim 3, characterized in that Solving the position control optimization model based on the output equation and the state equation of the dual neural network to obtain the target control thrust includes: Solving the position control optimization model according to the state equation of the dual neural network to obtain the target optimization variable value; The target control thrust is determined according to the output equation of the dual neural network and the target optimization variable value.

5. The method according to claim 4, characterized in that The target planar motor is position controlled according to the target control thrust, including: Determining a target current corresponding to the target control thrust according to the current-control thrust conversion relationship; The target current is input into a current driver to obtain a target voltage, and the position of the target planar motor is controlled according to the target voltage.

6. A position control device for a planar motor, characterized in that: The device comprises: A prediction model determination module, used to determine a position prediction model of the target planar motor according to a discrete state space model of the target planar motor and the current position information, and to determine a speed prediction model according to the position prediction model and a preset discrete sampling time; wherein the state space model is used to describe the relationship between the position of the motor and the control thrust, and the control thrust is used to control the movement of the motor; A position control optimization model determination module, used to determine the position control optimization model of the target planar motor according to the reference position information of the target planar motor, the position prediction model and the speed prediction model; wherein the position control optimization model includes a target cost function and a control thrust constraint condition, the target cost function is established based on the control thrust, position error and speed error of the target planar motor, and the control thrust constraint condition is determined based on the current working characteristics of the target planar motor; A dual neural network determination module, used to convert the position control optimization model into a quadratic programming model, and determine the output equation and state equation of the dual neural network according to the dual model of the quadratic programming model; wherein the state equation is used to describe the relationship between the optimization variables at adjacent moments in the dual model, and the output equation is used to describe the relationship between the control thrust and the optimization variables; The motor position control module is used to solve the position control optimization model based on the output equation and state equation of the dual neural network to obtain the target control thrust, and perform position control on the target plane motor according to the target control thrust.

7. The device according to claim 6, characterized in that The device also includes a state space model discrete module, which is used to: Before determining the position prediction model of the target planar motor according to the discrete state space model of the target planar motor and the current position information, determining the continuous state space model of the target planar motor; The continuous state space model is discretized based on the preset discrete sampling time to obtain a discrete state space model.

8. The device according to claim 6 or 7, characterized in that The position control optimization model determination module is used to: Determine reference speed information according to the reference position information and the preset discrete sampling time; Determine a position error matrix according to the difference between the reference position information and the position prediction model, and determine a first parameter matrix according to the product of a first weight matrix and the position error matrix; Determine a second parameter matrix according to the product of the second weight matrix and the control thrust matrix; Determine a speed error matrix according to the difference between the reference speed information and the speed prediction model, and determine a third parameter matrix according to the product of a third weight matrix and the speed error matrix; Determine a target cost function according to the first parameter matrix, the second parameter matrix and the third parameter matrix; Determining a control thrust constraint condition according to a current operating range of the target planar motor and a current-control thrust conversion relationship; A position control optimization model of the target planar motor is determined according to the target cost function and the control thrust constraint condition.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the position control method of the planar motor according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the position control method of the planar motor according to any one of claims 1 to 5 when executed.

Images