Magnetic suspension bearing and control method of magnetic suspension bearing

Abstract

The invention discloses a magnetic suspension bearing and a control method of the magnetic suspension bearing. The magnetic suspension bearing comprises an electromagnetic coil, a first end cover, a second end cover, a permanent magnet bearing inner ring and a plurality of electromagnetic cores, the first end cover and the second end cover are arranged on the electromagnetic coil, the first end cover and the second end cover are arranged on the two sides of the electromagnetic coil respectively, and the first end cover is parallel to the second end cover; the permanent magnet bearing inner ring is placed in the electromagnetic ring; and each electromagnetic core is arranged in an annular space of the electromagnetic coil and is used for controlling the movement of the inner ring of the permanent magnet bearing. According to the embodiment of the invention, the bearing with a compact structure can be provided, the miniaturization of the bearing is realized, the manufacturing and mounting difficulty is reduced, and the occupied space is reduced.

Description

Technical Field

[0001] The invention relates to the field of bearings, and in particular to a magnetic suspension bearing and a control method for the magnetic suspension bearing. Background Art

[0002] As a new type of bearing technology, magnetic bearings have shown broad application potential in multiple high-tech fields with their advantages such as non-contact, wear-free, high speed and high precision.

[0003] However, the magnetic bearings in the prior art often have problems such as large size, high cost, and complex control system, which limit their application in a wider range of occasions. Summary of the invention

[0004] The present invention provides a magnetic suspension bearing and a control method for the magnetic suspension bearing, which can provide a bearing with a compact structure, realize miniaturization of the bearing, reduce the difficulty of manufacturing and installation, and reduce the excessive space occupied.

[0005] According to one aspect of the present invention, a magnetic levitation bearing is provided, comprising: an electromagnetic ring, a first end cover, a second end cover, a permanent magnetic bearing inner ring and a plurality of electromagnetic cores; the first end cover and the second end cover are arranged on the electromagnetic ring, the first end cover and the second end cover are respectively arranged on both sides of the electromagnetic ring, and the first end cover and the second end cover are parallel; the permanent magnetic bearing inner ring is placed inside the electromagnetic ring; each of the electromagnetic cores is placed in the inner ring space of the electromagnetic ring, and each of the electromagnetic cores is used to control the movement of the permanent magnetic bearing inner ring.

[0006] According to another aspect of the present invention, a control method for a magnetic bearing is provided, characterized by comprising:

[0007] Obtaining the real-time voltage of the magnetic bearing and determining the real-time pressure;

[0008] Get the optimal excitation current at the current moment;

[0009] The real-time pressure and the optimal excitation current at the current moment are input into the pressure prediction model for processing, and the predicted pressure at the next moment is output;

[0010] Inputting the predicted pressure at the next moment into a nonlinear optimizer for processing, and outputting the optimal excitation current at the next moment;

[0011] According to the optimal excitation current at the next moment, the voltage output by the magnetic bearing at the next moment is controlled.

[0012] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] 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 control method of the magnetic bearing described in any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the control method of the magnetic bearing described in any embodiment of the present invention when executed.

[0017] The technical solution of the embodiment of the present invention is that the magnetic levitation bearing includes an electromagnetic ring, a first end cover, a second end cover, a permanent magnetic bearing inner ring and an electromagnetic core, and the permanent magnetic bearing inner ring and the electromagnetic core are placed in the space formed by the electromagnetic ring, the first end cover and the second end cover. This can achieve a compact bearing structure, reduce the volume of the magnetic levitation bearing, simplify the manufacturing and installation difficulty, and can be installed and used in scenarios with limited space, which can meet the application requirements of small spaces.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended 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

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 is a structural schematic diagram of a magnetic suspension bearing provided according to an embodiment of the present invention;

[0021] Figure 2 is a structural schematic diagram of a magnetic suspension bearing provided according to an embodiment of the present invention;

[0022] Figure 3 is a schematic structural diagram of an inner ring of a permanent magnetic bearing provided according to an embodiment of the present invention;

[0023] Figure 4 is a schematic diagram of the structure of an electromagnetic coil provided according to an embodiment of the present invention;

[0024] Figure 5is a schematic structural diagram of a first end cover or a second end cover provided according to an embodiment of the present invention;

[0025] Figure 6 is a schematic structural diagram of a thrust electromagnetic core on an electromagnetic coil provided according to an embodiment of the present invention;

[0026] Figure 7 is a schematic diagram of a thrust coil connection provided according to an embodiment of the present invention;

[0027] Figure 8 is a schematic diagram of adjusting coil connection according to an embodiment of the present invention;

[0028] Fig. 9 is a schematic structural diagram of an inner ring of a permanent magnetic bearing provided according to an embodiment of the present invention;

[0029] Fig.10 is a flow chart of a control method of a magnetic bearing provided according to an embodiment of the present invention;

[0030] Fig.11 is a schematic diagram of the structure of a pressure prediction model provided according to an embodiment of the present invention;

[0031] Fig.12 is a schematic diagram of a control method for a magnetic bearing provided according to an embodiment of the present invention;

[0032] Fig.13 is a schematic structural diagram of a control device for a magnetic bearing provided according to an embodiment of the present invention;

[0033] Fig.14 It is a structural schematic diagram of an electronic device for implementing the control method of the magnetic suspension bearing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] Figure 1 A schematic structural diagram of a magnetic bearing provided in an embodiment of the present invention.

[0037] The magnetic bearing comprises: an electromagnetic ring 1, a first end cover 2-A, a second end cover 2-B, a permanent magnetic bearing inner ring 13 and a plurality of electromagnetic cores. The first end cover 2-A and the second end cover 2-B are arranged on the electromagnetic ring, and the first end cover 2-A and the second end cover 2-B are arranged on both sides of the electromagnetic ring 1 respectively, and the first end cover 2-A and the second end cover 2-B are parallel; the permanent magnetic bearing inner ring 13 is placed inside the electromagnetic ring 1; each electromagnetic core is placed in the inner ring space of the electromagnetic ring 1, and each electromagnetic core is used to control the movement of the permanent magnetic bearing inner ring 13.

[0038] The multiple electromagnetic cores are used to control the movement of the permanent magnetic bearing inner ring 13 in multiple directions, for example, the directions may include axial direction and radial direction.

[0039] The electromagnetic core includes an electromagnetic core 8 and an electromagnetic core 1-A, wherein the electromagnetic core 8 is placed on the end cover, the electromagnetic core 1-A is placed on the electromagnetic coil 1, and the electromagnetic cores are all placed in the internal space formed by the electromagnetic coil 1 and the two end covers. The electromagnetic core has no contact with the inner ring 13 of the permanent magnetic bearing. The electromagnetic core 8 and the electromagnetic core 1-A are used to generate a magnetic field by energizing to control the movement of the inner ring 13 of the permanent magnetic bearing in different directions, wherein the movement direction of the inner ring 13 of the permanent magnetic bearing controlled by the electromagnetic core 8 is perpendicular to the movement direction of the inner ring 13 of the permanent magnetic bearing controlled by the electromagnetic core 1-A. In this way, by integrating the axial magnetic suspension bearing with the radial magnetic suspension bearing, a three-degree-of-freedom hybrid magnetic suspension bearing with a compact structure is realized. In addition, except for a small number of components such as the electromagnetic core, the proposed magnetic suspension bearing is made of aluminum alloy as a whole, and the adjustment device and the bearing are designed as a whole, which reflects its advantages of miniaturization and lightweight compared with the existing magnetic suspension bearings.

[0040] The technical solution of the embodiment of the present invention is that the magnetic levitation bearing includes an electromagnetic ring, a first end cover, a second end cover, a permanent magnetic bearing inner ring and an electromagnetic core, and the permanent magnetic bearing inner ring and the electromagnetic core are placed in the space formed by the electromagnetic ring, the first end cover and the second end cover. This can achieve a compact bearing structure, reduce the volume of the magnetic levitation bearing, simplify the manufacturing and installation difficulty, and can be installed and used in scenarios with limited space, which can meet the application requirements of small spaces.

[0041] Figure 2 A structural schematic diagram of a magnetic bearing is provided, wherein a first end cover 2-A and a second end cover 2-B are fixedly mounted on an electromagnetic ring 1 by assembling a plurality of screws 3, and the first end cover 2-A and the second end cover 2-B are respectively assembled on both sides of the electromagnetic ring 1. The first end cover 2-A and the second end cover 2-B are respectively assembled on the electromagnetic ring 1 by 6 screws 3. The inner ring 13 of the permanent magnetic bearing is freely placed inside the electromagnetic ring 1.

[0042] Figure 3 A structural schematic diagram of a permanent magnetic bearing inner ring 13 is provided. The permanent magnetic bearing inner ring is an annular structure.

[0043] In some embodiments, the multiple electromagnetic cores include at least one thrust electromagnetic core and at least one adjustment electromagnetic core; each thrust electromagnetic core is arranged on the inner surface of the electromagnetic ring, and an adjustment electromagnetic core is arranged on the inner surface of the first end cover and the inner surface of the second end cover; the inner surface of the first end cover and the inner surface of the second end cover are opposite to the inner ring of the permanent magnet bearing.

[0044] Among them, the thrust electromagnetic core is used to control the movement of the inner ring of the permanent magnetic bearing in the X-axis direction, and to control the movement of the inner ring of the permanent magnetic bearing in the Y-axis direction. The adjustment electromagnetic core is used to control the movement of the inner ring of the permanent magnetic bearing in the Z-axis direction. The inner surface on which the thrust electromagnetic core is installed and the inner surface on which the adjustment electromagnetic core is installed are perpendicular to each other. Therefore, the movement direction controlled by the thrust electromagnetic core is perpendicular to the movement direction controlled by the adjustment electromagnetic core, and they are independent of each other and will not interfere with each other, thereby realizing the movement of the inner ring of the permanent magnetic bearing in multiple directions, and the inner rings of the permanent magnetic bearings moving in different directions are integrated together to realize a compact structure of the inner ring of the permanent magnetic bearing. The inner surface of the electromagnetic ring, the inner surface of the first end cover, and the inner surface of the second end cover are all opposite to the inner ring of the permanent magnetic bearing. Figure 1 As shown, a plurality of thrust electromagnetic cores 1-A are mounted on the inner surface of the electromagnetic ring 1 close to the inner ring 13 of the permanent magnetic bearing, a plurality of adjustment electromagnetic cores 8 are mounted on the inner surface of the first end cover 2-A close to the inner ring 13 of the permanent magnetic bearing, and a plurality of adjustment electromagnetic cores 8 are mounted on the inner surface of the first end cover 2-A close to the inner ring 13 of the permanent magnetic bearing. Usually, the thrust electromagnetic cores 1-A appear in pairs, and the adjustment electromagnetic cores 8 appear in pairs.

[0045] Figure 4A schematic diagram of the structure of an electromagnetic coil is provided. Figure 4 As shown, 12 thrust electromagnetic cores 1-A are arranged on the electromagnetic coil. Figure 5 A schematic diagram of the structure of a first end cap or a second end cap is provided. Figure 5 As shown, the first end cover 2 -A or the second end cover 2 -B is provided with 12 adjustment electromagnetic cores 8 .

[0046] By installing electromagnetic cores on surfaces in different directions, the inner ring of the same permanent magnetic bearing can be moved in different directions, and the bearings moving in different directions can be integrated together to reduce the volume of the bearing.

[0047] In some embodiments, a thrust coil is provided on the thrust electromagnetic core, the first end of the thrust coil is connected to the thrust electromagnetic core, the second end of the thrust coil is provided with a radial anti-collision gasket, a first number of thrust coils are connected in series, a second number of thrust coils are connected in series, and the first number is the same as the second number; the first end of the adjustment electromagnetic core is connected to the first end cover or the second end cover, the second end of the adjustment electromagnetic core is provided with an axial anti-collision gasket, a third number of adjustment electromagnetic cores are connected in series, a fourth number of adjustment electromagnetic cores are connected in series, and the third number is the same as the fourth number; a Hall sensor is provided between two adjacent pairs of adjustment electromagnetic cores; the adjustment electromagnetic core pair includes two adjacent adjustment electromagnetic cores.

[0048] The coil is used to generate a magnetic field by energizing it. In order to reduce interference and cost between the coils, the same number of coils can be set in each direction of movement. The first number, the second number, the third number and the fourth number are 6. The Hall sensor is used to measure the position of the rotor. When the sensor is placed in a magnetic field and a current passes through it, a Hall voltage is generated in a direction perpendicular to the current and the magnetic field. By measuring the Hall voltage, the strength and direction of the magnetic field can be determined, which is then used to measure the position of the rotor. Thereafter, the real-time pressure can be calculated based on the change in the rotor position.

[0049] Figure 6 A schematic diagram of the structure of a thrust electromagnetic core on an electromagnetic coil is provided, such as Figure 6 As shown, a thrust coil 4 is mounted on the thrust electromagnetic core 1-A, and a radial anti-collision gasket 5 is disposed at the end of the thrust electromagnetic core.

[0050] Figure 7A schematic diagram of thrust coil wiring is provided. In order to reduce the control difficulty, the 12 thrust electromagnetic cores 1-A on the electromagnetic coil 1 are divided into two groups. Among them, the thrust coils of the thrust electromagnetic cores 1-A2, 1-A3, 1-A4, 1-A8, 1-A9, and 1-A10 are connected in series, and are jointly responsible for the adjustment of the inner ring of the permanent magnetic bearing in the X-axis direction; the thrust coils of the thrust electromagnetic cores 1-A1, 1-A5, 1-A6, 1-A7, 1-A11, and 1-A12 are connected in series, and are jointly responsible for the adjustment of the inner ring of the permanent magnetic bearing in the Y-axis direction. The embodiment of the present invention has more thrust coils. Increasing the number of thrust coils can increase the thrust magnetic field strength, thereby increasing the adjustment speed of the position of the inner ring of the permanent magnetic bearing.

[0051] like Figure 5 As shown, the first end cover or the second end cover is provided with 6 Hall sensors, and an axial anti-collision gasket 9 is provided at the end of the adjustment electromagnetic core.

[0052] Figure 8 A schematic diagram for adjusting the coil wiring is provided. Figure 8 As shown, similar to the processing method of the thrust coil, the adjustment coils of the 24 adjustment electromagnetic cores on the first end cover 2-A and the second end cover 2-B are connected in series and are jointly responsible for the adjustment of the inner ring of the permanent magnetic bearing in the Z-axis direction. By increasing the number of adjustment coils, the adjustment magnetic field strength is increased, and the adjustment speed of the Z-axis position of the inner ring of the permanent magnetic bearing is improved.

[0053] By equipping the end of the electromagnetic core with an anti-collision gasket, the safety of the inner ring of the permanent magnetic bearing can be increased. By configuring a Hall sensor between the adjustment electromagnetic cores, the safety and stability of the inner ring of the permanent magnetic bearing can be improved. In addition, 6 electromagnetic cores are configured in the X-axis direction, Y-axis direction and Z-axis direction respectively to control the direction of the inner ring of the permanent magnetic bearing. By increasing the number of thrust electromagnetic cores and adjustment electromagnetic cores, the control electromagnetic force of the magnetic levitation bearing is improved and the control speed is accelerated.

[0054] In some embodiments, the inner ring of the permanent magnet bearing includes: a permanent magnet bracket, radial permanent magnets and axial permanent magnets; the radial permanent magnets are arranged on the outer ring of the permanent magnet bracket, and the axial permanent magnets are respectively installed on both sides of the permanent magnet bracket. The radial permanent magnets and the magnetic poles of the electromagnetic ring are assembled in the same sex, and the axial permanent magnets and the magnetic poles of the first end cover and the second end cover are assembled in the same sex.

[0055] Fig. 9 A structural schematic diagram of the inner ring of a permanent magnetic bearing is provided, such as Fig. 9 As shown, the inner ring 13 of the permanent magnet bearing is composed of a permanent magnet bracket 10, a radial permanent magnet 12 and an axial permanent magnet 11. The radial permanent magnet is mounted on the outer ring of the permanent magnet bracket, and the axial permanent magnets are mounted on both sides of the permanent magnet bracket; during the pre-installation process of the magnetic suspension bearing, the radial permanent magnet and the magnetic poles of the electromagnetic ring are assembled in the same sex, and the axial permanent magnet and the magnetic poles of the end cover are assembled in the same sex.

[0056] By configuring the inner ring of the permanent magnetic bearing to include radial permanent magnets and axial permanent magnets, the inner ring of the permanent magnetic bearing can move in the magnetic field generated by the electromagnetic core in both axial and radial directions, and by assembling the radial permanent magnets and the electromagnetic ring poles in the same sex, and assembling the axial permanent magnets and the end cover poles in the same sex, the inner ring of the permanent magnetic bearing can be suspended in the axial and radial directions.

[0057] Fig.10 A flow chart of a control method for a magnetic bearing provided by an embodiment of the present invention. The embodiment of the present invention can be applied to controlling the suspension and rotation of the inner ring of a bearing in a magnetic bearing. The method can be executed by a control device of the magnetic bearing. The control device of the magnetic bearing can be implemented in the form of hardware and / or software. The control device of the magnetic bearing can be configured in an electronic device with a certain data computing capability, and the electronic device can be a server or a client.

[0058] See also Fig.10 The control method of the magnetic bearing shown is applied to the magnetic bearing as described in any embodiment of the present invention, and specifically includes:

[0059] S1001. Obtain the real-time voltage of the magnetic bearing and determine the real-time pressure.

[0060] The real-time voltage may refer to the voltage at the current moment at the two ends of the electromagnetic core that outputs the electromagnetic field in the magnetic bearing. The real-time pressure may refer to the pressure at the current moment. The real-time voltage can be converted into the real-time pressure. The pressure is caused by the external force (such as gravity, axial and / or radial thrust from the outside) on the rotor in each axial direction. The coil keeps the rotor suspended by generating thrusts of the same amplitude and opposite directions. The pressure calculation is to measure the position change of the rotor in the X-axis, Y-axis and Z-axis directions respectively by the Hall sensor, and calculate the pressure change of the rotor in each axial direction. The specific formula is as follows.

[0061]

[0062] In the formula, F j It is the resultant force (pressure) of the rotor in each axial direction. The resultant force is the vector sum of the electromagnetic force and the external force. K pj It is the stiffness system of the system in each axis direction, which is related to the design and control parameters of the magnetic bearing and is measured through experiments. j It is the displacement of the rotor in each axial direction, which is obtained by looking up a table based on the output signal of the Hall sensor. The table comes from the sensor manufacturer and is used to realize the mapping between the sensor output voltage signal and the rotor position.

[0063] S1002. Obtain the optimal excitation current at the current moment.

[0064] The optimal excitation current may refer to a control current input to the electromagnetic core so that the electromagnetic core outputs a desired magnetic field.

[0065] S1003: Input the real-time pressure and the optimal excitation current at the current moment into a pressure prediction model for processing, and output the predicted pressure at the next moment.

[0066] The pressure prediction model is used to predict the future output pressure based on the real-time pressure and the optimal excitation current at the current moment. The next moment represents the future moment. The predicted pressure may refer to the pressure corresponding to the voltage at both ends of the electromagnetic core at the future moment. Fig.11 A schematic diagram of the structure of a pressure prediction model is provided. Fig.11 As shown in Figure 1, the pressure prediction model includes an input layer, a hidden layer, and an output layer. The input layer contains 6 nodes, namely I x_opt ,I y_opt ,I z_opt , and the current output F x (k) (i.e. F in the figure) x )、F y (k) (i.e. F in the figure) y ) and F z (k). The output layer contains 3 nodes, which are the predicted value F at the next moment xm (k+1) (i.e. F xm )、F ym (k+1) (i.e. F ym ) and F zm (k+1) (i.e. F zm ). Where k represents the current moment and k+1 represents the next moment. The hidden layer contains 6 nodes. x Direction thrust Figure 7 The coils 1-A2, 1-A3, 1-A4, 1-A8, 1-A9 and 1-A10 shown are connected in series to reduce the control difficulty. y Direction thrust Figure 7 The thrust in the Fz direction is generated by the coils 1-A1, 1-A11, 1-A12, 1-A5, 1-A6 and 1-A7 shown, which are connected in series. The thrust in the Fz direction is generated by the coils on the end caps, which are connected in series.

[0067] Among them, the input-output relationship of the hidden layer is shown in Formula 1.

[0068] (1)

[0069] In the formula, represents the weight coefficient of the hidden layer, f1 represents the activation function, which is a hyperbolic tangent function. O2 represents the output signal of the neurons in the second layer (hidden layer) of the neural network, and net2 is the linear part of the neuron model in this layer.

[0070] The input-output relationship of the output layer is shown in Equation 2.

[0071] (2)

[0072] In the formula, represents the weight coefficient of the output layer, f2 represents the activation function, which is the ReLU function. O3 represents the output signal of the neurons in the third layer (output layer) of the neural network, and net3 is the linear part of the neuron model in this layer.

[0073] In some embodiments, in some embodiments, the pressure prediction model is trained as follows: obtaining training data, the training data is determined based on the historical operation data and / or test data of the magnetic levitation bearing, and the training data includes: the standard pressure at a first moment, the optimal excitation current at a first moment, and the standard pressure at a second moment; inputting the standard pressure and the optimal excitation current at the first moment into the pressure prediction model for processing, and outputting the predicted pressure at the second moment; adjusting the parameters of the pressure prediction model according to the standard pressure at the second moment and the predicted pressure at the second moment to obtain a trained pressure prediction model.

[0074] The training data of the pressure detection model comes from the exit test data and / or historical operation data of the three-degree-of-freedom magnetic bearing. The historical operation data may refer to the data collected by running the magnetic bearing at a historical moment. The exit test data may refer to the data collected during the test of the magnetic bearing. The standard pressure may refer to the pressure obtained by converting the voltage actually measured. The second moment is after the first moment, which is equivalent to taking the data of the first moment in history as input to obtain the data of the second moment in the future. The predicted pressure at the second moment may refer to the predicted result output by the pressure detection model. The standard pressure at the second moment may be understood as the true value, and the predicted pressure at the second moment may refer to the predicted value. The value of the loss function can be calculated based on the standard pressure at the second moment and the predicted pressure at the second moment, and the parameters of the pressure prediction model can be adjusted based on the value of the loss function. The differential result of the loss function L is the gradient of L relative to the model parameters, which is used for parameter update in the back propagation stage.

[0075] Through mechanism modeling, the mathematical model of the three-degree-of-freedom magnetic bearing is established. The loss function L is shown in Formula 3:

[0076] (3)

[0077] In the formula, is the vacuum magnetic permeability. Ar is the projected area of ​​the radial magnetic pole, which can be obtained through ANSYS software simulation analysis. cx1 , Φ cx2 , Φ cy1 , Φ cy2 and Φ cz are the controlled magnetic flux of the magnetic bearing in the X-axis direction, Y-axis direction and Z-axis direction, as shown in Equation 4; Φ px1 , Φ px2 , Φ py1 , Φ py2 , Φ pz1 and Φ pz2 They are the magnetic flux of the inner ring of the permanent magnet bearing in the X-axis direction, Y-axis direction and Z-axis direction, as shown in Formula 5-7.

[0078] (4)

[0079] (5)

[0080] (6)

[0081] (7)

[0082] In formula 4-7, N r is the number of turns of radial excitation coil, N z is the number of turns of the axial excitation coil, k i Represents the magnetic resistance of each part of the radial bearing, R y is the magnetic resistance of the stator yoke, R iz is the soft magnetic reluctance, R1~R6 are the reluctance of each axial part, R m is the permanent magnet reluctance, R s is the leakage magnetic resistance. scz is the equivalent magnetic resistance of the leakage magnetic circuit in the radial control magnetic field, R ib is the soft magnetic reluctance of the bias magnetic circuit. m is the magnetomotive force generated by the inner ring of the permanent magnetic bearing. All the above-mentioned magnetic resistances are constants. The axial and radial three-dimensional magnetic fields can be equivalent to a two-dimensional equivalent model through the ANSYS axisymmetric model. After simulation, the values ​​of the above parameters can be obtained.

[0083] In the embodiment of the present invention, the loss function L shown in Formula 3 embeds the mathematical model of the magnetic bearing (Formula 4-Formula 7). The mathematical model in the loss function provides guidance for the parameter optimization direction of the neural network model. The ultimate desired effect is that under the same input, the neural network model and the mathematical model have similar outputs. The differential result of the loss function L is the gradient of L relative to the model parameters, which is used for parameter update in the back propagation stage. During the back propagation process:

[0084] (1) Define functions and variables: variables are the parameters of each neuron; the function is a composite function, the outer function is the loss function L, and the inner function is the forward propagation function of the neural network model (that is, the neural network model itself).

[0085] (2) Constructing a computational graph: In a neural network, each operation is considered a node in a computational graph. The computational graph records all sequences of operations from input to output.

[0086] (3) Initialize the gradient: At the end of the computational graph, that is, at the output node, the gradient is initialized to a vector of all 1s. This represents the rate of change of the output with respect to itself.

[0087] (4) Backpropagation: Starting from the output node, the gradient is propagated backward (toward the input direction) along the computational graph. At each node, the chain rule is applied to calculate and update the gradient.

[0088] (5) Calculate the gradient: At each node, the gradient is updated using the derivative of the operation corresponding to the node. This process continues until the input node of the computational graph is reached.

[0089] (6) Storing gradients: Store the calculated gradients at each node. For input nodes, these gradients are the derivatives of the function with respect to the input variables (model parameters).

[0090] (7) Reading gradients: Once all nodes in the computational graph have calculated and stored the gradients, the derivatives can be read from the input nodes.

[0091] In the embodiment of the present invention, through the deep learning framework, when a model is built and the back propagation function is called, the gradient of each node in the entire calculation graph is automatically calculated, and these gradients are used to update the parameters of the model.

[0092] Add a parameter update function as shown below.

[0093]

[0094] This formula introduces a momentum term, which means that when updating parameters, not only the current gradient is considered, but also the previous gradient direction and magnitude, so as to accumulate momentum during the optimization process. This can reduce random oscillations in the flat area of ​​the objective function, and can accelerate the learning process when the gradient direction is consistent, and reduce the update amplitude when the gradient direction is inconsistent.

[0095] In the formula, θ is the parameter of the model; vt is the momentum term, as shown in the following formula.

[0096]

[0097] Where γ is the momentum coefficient (determined by experiments to be 0.5), η is the learning rate (determined by experiments to be 0.02), is the gradient of the loss function L with respect to the parameter θ.

[0098] By pre-training the stress detection model, the efficiency and accuracy of stress detection can be improved.

[0099] S1004: input the predicted pressure at the next moment into a nonlinear optimizer for processing, and output the optimal excitation current at the next moment.

[0100] S1005. Control the voltage output by the magnetic bearing at the next moment according to the optimal excitation current at the next moment.

[0101] In some embodiments, the real-time voltage includes: the voltage of the magnetic bearing in the X-axis direction, the voltage in the Y-axis direction, and the voltage in the Z-axis direction; the optimal excitation current includes the optimal excitation current in the X-axis direction, the optimal excitation current in the Y-axis direction, and the optimal excitation current in the Z-axis direction; the controlling the voltage output by the magnetic bearing at the next moment according to the optimal excitation current at the next moment includes: controlling the current flowing through the X-axis coil in the magnetic bearing according to the optimal excitation current in the X-axis direction at the next moment; controlling the current flowing through the Y-axis coil in the magnetic bearing according to the optimal excitation current in the Y-axis direction at the next moment; and controlling the current flowing through the Z-axis coil in the magnetic bearing according to the optimal excitation current in the Z-axis direction at the next moment.

[0102] By dividing the voltage, pressure and current into three directions for calculation, the control data of the magnetic bearing in three directions can be accurately calculated, and the movement of the magnetic bearing can be precisely controlled.

[0103] In some embodiments, the predicted pressure at the next moment is input into a nonlinear optimizer for processing, and the optimal excitation current at the next moment is output, including: inputting the predicted pressure at the next moment into the nonlinear optimizer; through the nonlinear optimizer, according to the predicted pressure at the next moment, the predicted time domain length, the control time domain length, the reference pressure and the weighting coefficient, calculating the excitation current corresponding to the minimum cost, so as to obtain the optimal excitation current at the next moment.

[0104] The nonlinear optimizer is used to determine the optimal control signal, that is, the optimal excitation current. The input of the nonlinear optimizer includes the predicted pressure at the next moment and the reference pressure at the current moment. The nonlinear optimizer calculates the cost based on the predicted pressure at the next moment and the reference pressure at the current moment, and solves the excitation current with the minimum cost as the optimization goal, and determines the solved excitation current as the optimal excitation current at the next moment.

[0105] Construct the cost function of the nonlinear optimizer and perform rolling optimization to minimize it to determine the optimal control signal, that is, the optimal excitation current I opt , the cost function is:

[0106] (8)

[0107] In the formula, J is the cost function, N p is the predicted time domain length, N u is the control time domain length, I is the control input signal, i.e., the excitation current, Fj_ref is the pressure reference value, Fjm is the response output value of the neural network prediction model, λ is the weighting coefficient, and k is the current moment. Fj_ref is the general name of Fx_ref, Fy_ref, and Fz_ref. Fjm is the general name of Fxm, Fym, and Fzm.

[0108] By constructing a nonlinear optimizer, the optimal excitation current with the minimum cost can be iteratively obtained, thereby reducing the use cost of the magnetic bearing.

[0109] In some embodiments, controlling the voltage output by the magnetic bearing at the next moment according to the optimal excitation current at the next moment includes: inputting the optimal excitation current at the next moment into the control system for processing, and outputting the control current at the next moment; controlling the voltage output by the magnetic bearing at the next moment according to the control current at the next moment; obtaining the real-time pressure at the next moment; obtaining the real-time control error according to the difference between the real-time pressure at the next moment and the predicted pressure at the next moment; and adjusting the reference pressure of the nonlinear optimizer according to the real-time control error.

[0110] In fact, the optimal excitation current is used to dynamically control the magnetic bearing, and feedback correction is continuously performed until the magnetic bearing reaches a stable state. The control system may include a current controller and a pulse width adjustment converter. The control system is used to process the difference between the optimal excitation current at the next moment and the output control current at the current moment, and output the control current at the next moment. The control current at the next moment is provided to the magnetic bearing to control the voltage output by the magnetic bearing at the next moment to be the expected voltage. The voltage output by the magnetic bearing at the next moment is actually the voltage at both ends of the coil in the magnetic bearing. The real-time pressure at the next moment may refer to the actual pressure collected by the magnetic bearing at the next moment. The real-time control error is used to describe the difference between the expected pressure and the actual pressure, that is, the real-time control error can be understood as the feedback result obtained by dynamic adjustment. The real-time control error is provided to the nonlinear optimizer as a feedback result, so that the nonlinear optimizer can be dynamically adjusted according to the feedback result in real time. That is, when the next moment is reached, based on the difference between the real-time pressure at the next moment and the predicted pressure at the next moment, it is detected whether the pressure of the magnetic bearing at the next moment reaches the expected value (predicted pressure), and the magnetic bearing is continued to be adjusted according to the difference until the magnetic bearing reaches the predicted pressure.

[0111] Feedback correction uses the current prediction error to correct the future reference output. At the current control time k, the control system obtains the actual output F(k) of the controlled object by measuring the output of the system, and obtains the error e(k) by comparing it with the predicted output Fm(k) at time k-1, as shown in Equation 9. Among them, the controlled object is the inner ring of the permanent magnetic bearing, and the controlled variable is the pressure of the inner ring of the permanent magnetic bearing in each axial direction.

[0112] (9)

[0113] This error e(k) can be used to correct the reference output, as shown in Equation 10.

[0114] (10)

[0115] Where λ is the correction coefficient, and the corrected reference output Instead of a given reference output F ref (k+1) to achieve rolling optimization and complete feedback correction.

[0116] Feedback correction can assist the nonlinear optimizer to dynamically adjust the excitation current in a timely manner to achieve rapid and stable realization of the magnetic suspension bearing to a stable state.

[0117] In some embodiments, inputting the optimal excitation current at the next moment into a control system for processing and outputting the control current at the next moment includes: calculating the current difference between the optimal excitation current at the next moment and the control current at the current moment; inputting the current difference into a control system for processing and outputting the control current at the next moment, and the control system includes a current controller and a pulse width adjustment converter.

[0118] The current difference is used to describe the current that needs to be adjusted at the next moment relative to the current moment. In fact, the control current is used to output directly to the coil. The current controller can be a proportional-integral current controller, which adjusts the current by both proportional and integral control methods to ensure that the system has no steady-state error after entering the steady state. The pulse width modulation converter is a method of digitally encoding the analog signal level by adjusting the duty cycle of the square wave to encode the analog signal level.

[0119] The control current at the next moment is determined by the current difference between the optimal excitation current at the next moment and the control current at the current moment, and the current can be adjusted by feedback to make the magnetic bearing enter a steady state.

[0120] The embodiment of the present invention designs a compact three-degree-of-freedom magnetic bearing. The magnetic bearing is mainly composed of four parts: an electromagnetic ring, two end covers, and a permanent magnetic bearing inner ring, and has a compact design. The magnetic bearing is made of aluminum alloy as a whole except for the electromagnetic core, achieving the design advantages of miniaturization and lightweight. An adjustment electromagnetic core and a Hall sensor are provided on the end cover, and an axial anti-collision gasket is provided at the end to enhance safety and stability. The inner ring of the permanent magnetic bearing is composed of a permanent magnet bracket, a radial permanent magnet, and an axial permanent magnet, and a homogeneous assembly method is adopted to optimize the magnetic field configuration. By increasing the number of thrust electromagnetic cores and adjustment electromagnetic cores, the control electromagnetic force of the magnetic bearing is improved, and the control speed is accelerated.

[0121] Fig.12 A schematic diagram of a control method for a magnetic bearing is provided. Fig.12 As shown in the figure, the pressure prediction model predictive control is used as the control algorithm of the magnetic bearing to achieve high-precision and high-efficiency control of the position of the inner ring of the bearing. The symbol " / 3" indicates that the signal consists of 3 components, namely Fx_ref, Fy_ref and Fz_ref. VH is the output signal of each Hall sensor. The symbol " / 12" indicates that the signal consists of 12 components, which are the output signals of each Hall sensor. By embedding the mechanism model of the magnetic bearing into the cost function of the neural network, the established pressure prediction model utilizes prior knowledge and reduces the demand for training data. The controller uses physical information neural network predictive control to fine-tune the position of the inner ring of the bearing, significantly reducing the vibration amplitude and noise level, and improving system performance.

[0122] The embodiments of the present invention have the following advantages:

[0123] (1) Miniaturization and lightweight: The magnetic bearing is made of aluminum alloy and combined with an overall design. Compared with existing technologies, it has achieved miniaturization and lightweight, reducing manufacturing costs and installation space requirements.

[0124] (2) High-precision and high-efficiency control: The magnetic bearing control system combines the advantages of physical information neural network and model predictive control to achieve high-precision and high-efficiency control of the bearing inner ring position, thereby improving the overall performance and stability of the system.

[0125] (3) Enhanced safety: By increasing the number of thrust electromagnetic cores and adjustment electromagnetic cores, the control speed of the system is improved. At the same time, by configuring anti-collision gaskets, the collision damage in extreme situations is reduced, ensuring the safe operation of the system.

[0126] (4) Reduce noise and vibration: The pressure prediction model predictive controller achieves optimal control of the position of the inner ring of the bearing, significantly reducing the vibration amplitude and noise level during operation and improving the user experience.

[0127] In summary, this technical solution has achieved remarkable technical effects such as miniaturization, lightweight, high-precision control, enhanced safety, reduced noise and vibration of magnetic levitation bearings and their control systems through innovative design and optimized control strategies, and has broad application potential and market prospects.

[0128] In an application scenario, an embodiment of the present invention provides a specific application solution of a magnetic bearing and its control system in a vertical axis wind turbine with small and medium power levels. This embodiment aims to achieve low noise, small space occupation and low-cost power generation. By adopting a compact and lightweight magnetic bearing and an advanced control system, the performance and economic benefits of the wind turbine are significantly improved.

[0129] The magnetic bearing and its control system in the embodiment of the present invention are composed of two parts: a magnetic bearing and a dedicated control system. The magnetic bearing is made of lightweight materials such as aluminum alloy, has a compact structure, and is mainly composed of electromagnetic rings, end covers, and permanent magnetic bearing inner rings. Through the action of electromagnetic force, the bearing is suspended and operates stably, effectively reducing mechanical friction and vibration.

[0130] The control system adopts a pressure prediction model predictive controller, which uses advanced neural network algorithms to make fine and smooth adjustments to the position of the inner ring of the bearing, significantly reducing the vibration amplitude and noise level during operation, and improving the overall performance of the system and user experience.

[0131] The magnetic bearing and its control system in this embodiment are applied to vertical axis wind turbines of small and medium power levels. The specific scheme is as follows:

[0132] (1) Installation and configuration of magnetic bearings: Magnetic bearings are installed on the rotating shaft of the wind turbine to replace traditional mechanical bearings. The configuration and parameters of the electromagnetic ring, end cover, and inner ring of the permanent magnetic bearing are adjusted according to the specific parameters and requirements of the wind turbine.

[0133] (2) Control system setup and debugging: Connect the control system to the wind turbine control system. Set up and debug the control system to ensure that it can accurately monitor and control the operating status of the magnetic bearing.

[0134] (3) Operation and testing: Start the wind turbine and start the magnetic bearing to operate. Monitor and test the operation status of the wind turbine and record key indicators such as noise, vibration, and power generation efficiency.

[0135] Through the application of this embodiment, the vertical axis wind turbines of small and medium power levels are expected to achieve the following significant effects:

[0136] Low-noise power generation: Due to the use of magnetic bearings, the noise of wind turbines during power generation is significantly reduced, meeting the requirements of environmental protection and comfort.

[0137] Small space occupation: The compact and lightweight design of the magnetic bearing reduces the overall volume of the wind turbine and improves land utilization.

[0138] Low-cost power generation: The optimized design of magnetic bearings and their control systems reduces the manufacturing and maintenance costs of wind turbines and improves economic benefits.

[0139] In summary, the application of the magnetic bearing and its control system provided in this embodiment to the vertical axis wind turbine with small and medium power levels has significant advantages of low noise, small space occupation and low cost power generation. These advantages not only improve the performance and economic benefits of the wind turbine, but also make positive contributions to the promotion of green energy and sustainable development.

[0140] Fig.13 A schematic diagram of the structure of a control device for a magnetic bearing provided in an embodiment of the present invention. The embodiment of the present invention can be applied to the case of controlling a magnetic bearing, the device can execute a control method for a magnetic bearing, the device can be implemented in the form of hardware and / or software, and the device can be configured in an electronic device that carries a function with a certain data computing capability.

[0141] See also Fig.13 The control device of the magnetic bearing shown comprises:

[0142] The pressure acquisition module 1310 is used to acquire the real-time voltage of the magnetic bearing and determine the real-time pressure;

[0143] The current acquisition module 1320 is used to obtain the optimal excitation current at the current moment;

[0144] The pressure prediction module 1330 is used to input the real-time pressure and the optimal excitation current at the current moment into the pressure prediction model for processing, and output the predicted pressure at the next moment;

[0145] The current prediction module 1340 is used to input the predicted pressure at the next moment into the nonlinear optimizer for processing, and output the optimal excitation current at the next moment;

[0146] The bearing control module 1350 is used to control the voltage output by the magnetic bearing at the next moment according to the optimal excitation current at the next moment.

[0147] In some embodiments, the real-time voltage includes: the voltage of the magnetic bearing in the X-axis direction, the voltage in the Y-axis direction, and the voltage in the Z-axis direction; the optimal excitation current includes the optimal excitation current in the X-axis direction, the optimal excitation current in the Y-axis direction, and the optimal excitation current in the Z-axis direction;

[0148] The bearing control module 1350 is specifically used for:

[0149] According to the optimal excitation current in the X-axis direction at the next moment, controlling the current flowing through the X-axis coil in the magnetic bearing;

[0150] Controlling the current flowing through the Y-axis coil in the magnetic bearing according to the optimal excitation current in the Y-axis direction at the next moment;

[0151] According to the optimal excitation current in the Z-axis direction at the next moment, the current flowing through the Z-axis coil in the magnetic bearing is controlled.

[0152] In some embodiments, the control device of the magnetic bearing further includes:

[0153] Model training module, used to:

[0154] Acquire training data, where the training data is determined based on historical operation data and / or test data of the magnetic bearing, and the training data includes: a standard pressure at a first moment, an optimal excitation current at the first moment, and a standard pressure at a second moment;

[0155] Inputting the standard pressure and the optimal excitation current at the first moment into the pressure prediction model for processing, and outputting the predicted pressure at the second moment;

[0156] According to the standard pressure at the second moment and the predicted pressure at the second moment, the parameters of the pressure prediction model are adjusted to obtain a trained pressure prediction model.

[0157] In some embodiments, the current prediction module 1340 is specifically used to:

[0158] Inputting the predicted pressure at the next moment into a nonlinear optimizer;

[0159] The nonlinear optimizer calculates the excitation current corresponding to the minimum cost according to the predicted pressure at the next moment, the predicted time domain length, the control time domain length, the reference pressure and the weighting coefficient to obtain the optimal excitation current at the next moment.

[0160] In some embodiments, the bearing control module 1350 is specifically configured to:

[0161] Inputting the optimal excitation current at the next moment into the control system for processing, and outputting the control current at the next moment;

[0162] controlling the voltage output by the magnetic bearing at the next moment according to the control current at the next moment;

[0163] Obtaining the real-time pressure at the next moment;

[0164] Obtaining a real-time control error according to a difference between the real-time pressure at the next moment and the predicted pressure at the next moment;

[0165] The reference pressure of the nonlinear optimizer is adjusted according to the real-time control error.

[0166] In some embodiments, the current prediction module 1340 is specifically used to:

[0167] Calculating the current difference between the optimal excitation current at the next moment and the control current at the current moment;

[0168] The current difference is input into a control system for processing, and the control current at the next moment is output. The control system includes a current controller and a pulse width modulation converter.

[0169] The control device of the magnetic bearing provided in the embodiment of the present invention can execute the control method of the magnetic bearing provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0170] In the technical solutions of the embodiments of the present invention, the acquisition, storage and application of network traffic etc. involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0171] Fig.14 A schematic diagram of the structure of an electronic device 1400 that can be used to implement an embodiment 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 processing, 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 required herein.

[0172] like Fig.14 As shown, the electronic device 1400 includes at least one processor 1401, and a memory connected to the at least one processor 1401 in communication, such as a read-only memory (ROM) 1402, a random access memory (RAM) 1403, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 1401 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 1402 or the computer program loaded from the storage unit 1408 to the random access memory (RAM) 1403. In the RAM 1403, various programs and data required for the operation of the electronic device 1400 can also be stored. The processor 1401, the ROM 1402, and the RAM 1403 are connected to each other through a bus 1404. An input / output (I / O) interface 1405 is also connected to the bus 1404.

[0173] Multiple components in the electronic device 1400 are connected to the I / O interface 1405, including: an input unit 1406, such as a keyboard, a mouse, etc.; an output unit 1407, such as various types of displays, speakers, etc.; a storage unit 1408, such as a disk, an optical disk, etc.; and a communication unit 1409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1409 allows the electronic device 1400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0174] The processor 1401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 1401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special 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 1401 executes the various methods and processes described above, such as a distribution network line planning method.

[0175] In some embodiments, the distribution network line planning method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 1408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1400 via the ROM 1402 and / or the communication unit 1409. When the computer program is loaded into the RAM 1403 and executed by the processor 1401, one or more steps of the distribution network line planning method described above may be performed. Alternatively, in other embodiments, the processor 1401 may be configured to execute the distribution network line planning method in any other appropriate manner (e.g., by means of firmware).

[0176] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations 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 special purpose 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 data and instructions to the storage system, the at least one input device, and the at least one output device.

[0177] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0178] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0179] To provide interaction with a user, the systems and techniques described herein may 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 trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0180] The systems and techniques described herein may 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 with a graphical user interface or a web browser through which a user can interact with implementations 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 may 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.

[0181] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS (Virtual Private Server) services.

[0182] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0183] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A magnetic bearing, characterized in that: The magnetic levitation bearing includes: an electromagnetic ring, a first end cover, a second end cover, a permanent magnetic bearing inner ring and a plurality of electromagnetic cores; the first end cover and the second end cover are arranged on the electromagnetic ring, the first end cover and the second end cover are respectively arranged on both sides of the electromagnetic ring, and the first end cover and the second end cover are parallel; the permanent magnetic bearing inner ring is placed inside the electromagnetic ring; each of the electromagnetic cores is placed in the inner ring space of the electromagnetic ring, and each of the electromagnetic cores is used to control the movement of the permanent magnetic bearing inner ring.

2. The magnetic bearing according to claim 1, characterized in that: The multiple electromagnetic cores include at least one thrust electromagnetic core and at least one adjustment electromagnetic core; each of the thrust electromagnetic cores is arranged on the inner surface of the electromagnetic ring, and the adjustment electromagnetic core is arranged on the inner surface of the first end cover and the inner surface of the second end cover; the inner surface of the first end cover and the inner surface of the second end cover are opposite to the inner ring of the permanent magnet bearing.

3. The magnetic bearing according to claim 2, characterized in that: A thrust coil is arranged on the thrust electromagnetic core, the first end of the thrust coil is connected to the thrust electromagnetic core, the second end of the thrust coil is arranged with a radial anti-collision gasket, a first number of thrust coils are connected in series, a second number of thrust coils are connected in series, and the first number is the same as the second number; the first end of the adjustment electromagnetic core is connected to the first end cover or the second end cover, the second end of the adjustment electromagnetic core is arranged with an axial anti-collision gasket, a third number of adjustment electromagnetic cores are connected in series, and a fourth number of adjustment electromagnetic cores are connected in series, and the third number is the same as the fourth number; a Hall sensor is arranged between two adjacent pairs of adjustment electromagnetic cores; the adjustment electromagnetic core pair includes two adjacent adjustment electromagnetic cores.

4. The magnetic bearing according to claim 1, characterized in that: The inner ring of the permanent magnet bearing includes: a permanent magnet bracket, radial permanent magnets and axial permanent magnets; the radial permanent magnets are arranged on the outer ring of the permanent magnet bracket, and the axial permanent magnets are respectively installed on both sides of the permanent magnet bracket. The radial permanent magnets and the magnetic poles of the electromagnetic ring are assembled in the same sex, and the axial permanent magnets and the magnetic poles of the first end cover and the second end cover are assembled in the same sex.

5. A control method for a magnetic bearing, characterized in that: Applicable to the magnetic bearing according to any one of claims 1 to 4; the method comprises: Obtaining the real-time voltage of the magnetic bearing and determining the real-time pressure; Get the optimal excitation current at the current moment; The real-time pressure and the optimal excitation current at the current moment are input into the pressure prediction model for processing, and the predicted pressure at the next moment is output; Inputting the predicted pressure at the next moment into a nonlinear optimizer for processing, and outputting the optimal excitation current at the next moment; According to the optimal excitation current at the next moment, the voltage output by the magnetic bearing at the next moment is controlled.

6. The method according to claim 5, characterized in that The real-time voltage includes: the voltage of the magnetic bearing in the X-axis direction, the voltage in the Y-axis direction and the voltage in the Z-axis direction; the optimal excitation current includes the optimal excitation current in the X-axis direction, the optimal excitation current in the Y-axis direction and the optimal excitation current in the Z-axis direction; The step of controlling the voltage output by the magnetic bearing at the next moment according to the optimal excitation current at the next moment comprises: According to the optimal excitation current in the X-axis direction at the next moment, controlling the current flowing through the X-axis coil in the magnetic bearing; Controlling the current flowing through the Y-axis coil in the magnetic bearing according to the optimal excitation current in the Y-axis direction at the next moment; According to the optimal excitation current in the Z-axis direction at the next moment, the current flowing through the Z-axis coil in the magnetic bearing is controlled.

7. The method according to claim 6, characterized in that The training method of the pressure prediction model is as follows: Acquire training data, where the training data is determined based on historical operation data and / or test data of the magnetic bearing, and the training data includes: a standard pressure at a first moment, an optimal excitation current at the first moment, and a standard pressure at a second moment; Inputting the standard pressure and the optimal excitation current at the first moment into the pressure prediction model for processing, and outputting the predicted pressure at the second moment; According to the standard pressure at the second moment and the predicted pressure at the second moment, the parameters of the pressure prediction model are adjusted to obtain a trained pressure prediction model.

8. The method according to claim 5, characterized in that The step of inputting the predicted pressure at the next moment into a nonlinear optimizer for processing and outputting the optimal excitation current at the next moment comprises: Inputting the predicted pressure at the next moment into a nonlinear optimizer; The nonlinear optimizer calculates the excitation current corresponding to the minimum cost according to the predicted pressure at the next moment, the predicted time domain length, the control time domain length, the reference pressure and the weighting coefficient to obtain the optimal excitation current at the next moment.

9. The method according to claim 5, characterized in that The step of controlling the voltage output by the magnetic bearing at the next moment according to the optimal excitation current at the next moment comprises: Inputting the optimal excitation current at the next moment into the control system for processing, and outputting the control current at the next moment; controlling the voltage output by the magnetic bearing at the next moment according to the control current at the next moment; Obtaining the real-time pressure at the next moment; Obtaining a real-time control error according to a difference between the real-time pressure at the next moment and the predicted pressure at the next moment; The reference pressure of the nonlinear optimizer is adjusted according to the real-time control error.

10. The method according to claim 5, characterized in that The step of inputting the optimal excitation current at the next moment into the control system for processing and outputting the control current at the next moment comprises: Calculating the current difference between the optimal excitation current at the next moment and the control current at the current moment; The current difference is input into a control system for processing, and the control current at the next moment is output. The control system includes a current controller and a pulse width modulation converter.

Images