A method and device for determining the damping coefficient of a self-damping conductor

Abstract

The present invention provides a method and device for determining the damping coefficient of a self-damping conductor. The method comprises inputting physical parameters of the self-damping conductor into a pre-established neural network prediction model to obtain the equivalent bending stiffness of the self-damping conductor; determining the damping coefficient of the self-damping conductor according to the equivalent bending stiffness of the self-damping conductor; wherein the physical parameters comprise: the diameter, tension, frequency, elastic modulus and wire strand gap of the self-damping conductor; the present invention predicts the bending stiffness of the self-damping conductor by using a neural network model, thereby saving the time and economic cost of the test; and providing a solution formula for the self-damping coefficient, thereby solving the problem of calculating the self-damping coefficient in the prior art.

Description

Technical Field

[0001] The invention belongs to the technical field of power grid disaster prevention, and in particular relates to a method and a device for determining a damping coefficient of a self-damping conductor. Background Art

[0002] Self-damping conductors have excellent self-damping properties due to the gaps between their layers. Even under greater tension, their self-damping properties are still better than those of ordinary conductors, so the average operating tension can be increased.

[0003] After the self-damping conductor is used in the power grid, the tension value of the conductor is no longer limited by the average operating tension, but is controlled by the maximum tension. The average operating tension of the conductor can be increased by at least 3 to 5 percentage points, the sag can be significantly reduced, and the height of the straight tower can be reduced accordingly. The damping coefficient and bending stiffness are key parameters in the calculation of the self-damping conductor, but there is currently no calculation method for the damping coefficient and bending stiffness of the self-damping conductor, which brings difficulties to the calculation of the self-damping conductor. Summary of the invention

[0004] The invention provides a method and device for determining the damping coefficient of a self-damping conductor, and aims to provide a method for calculating the damping coefficient of the self-damping conductor.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] The present invention provides a method for determining the damping coefficient of a self-damping conductor, wherein the method comprises:

[0007] Inputting the physical parameters of the self-damping wire into a pre-established neural network prediction model to obtain the equivalent bending stiffness of the self-damping wire;

[0008] Determining a damping coefficient of the self-damping wire according to the equivalent bending stiffness of the self-damping wire;

[0009] The physical parameters include: diameter, tension, frequency, elastic modulus and strand gap of the self-damping conductor.

[0010] Preferably, the process of acquiring the pre-established neural network prediction model includes:

[0011] Performing a bending stiffness test experiment on the test wire to obtain the equivalent bending stiffness of the test wire;

[0012] The neural network prediction model is obtained by training the physical parameter data of the test wire as the input sample of the input layer of the BP neural network model and the equivalent bending stiffness data of the test wire as the output sample of the output layer of the BP neural network model.

[0013] Preferably, obtaining the damping coefficient of the self-damping wire according to the equivalent bending stiffness of the self-damping wire comprises:

[0014] Determining the damping power of the self-damping wire according to the equivalent bending stiffness of the self-damping wire;

[0015] The damping coefficient of the self-damping wire is determined according to the damping power of the self-damping wire.

[0016] Further, determining the damping power of the self-damping wire according to the equivalent bending stiffness of the self-damping wire comprises:

[0017] The damping power P of the self-damping conductor is determined by the following formula: c :

[0018]

[0019] Where m is the mass per unit length of the self-damping conductor; L is the length of the self-damping conductor; T is the tension of the self-damping conductor; V c is the self-damping conductor wave velocity; n is the nth order wavelength of the self-damping conductor; ω n is the nth order circular frequency of the self-damping wire; D is the diameter of the self-damping wire; k D is the equivalent diameter coefficient; EI is the equivalent bending stiffness of the self-damping conductor; parameter K0 = 0.001 ~ 0.006, parameter β0 = -0.2 ~ -0.8; f n is the nth-order frequency of the self-damping conductor; A is the single amplitude of the self-damping conductor.

[0020] Further, the determining the damping coefficient of the self-damping wire according to the damping power of the self-damping wire comprises:

[0021] The damping coefficient c of the self-damping conductor is determined as follows:

[0022]

[0023] Furthermore, the number of nodes in the hidden layer of the BP neural network model is 8 to 12.

[0024] The present invention provides a device for determining the damping coefficient of a self-damping conductor, wherein the device comprises:

[0025] A prediction module, used for inputting the physical parameters of the self-damping wire into a pre-established neural network prediction model to obtain the equivalent bending stiffness of the self-damping wire;

[0026] A determination module, used to determine the damping coefficient of the self-damping wire according to the equivalent bending stiffness of the self-damping wire;

[0027] The physical parameters include: diameter, tension, frequency, elastic modulus and strand gap of the self-damping conductor.

[0028] Preferably, the process of acquiring the pre-established neural network prediction model includes:

[0029] Performing a bending stiffness test experiment on the test wire to obtain the equivalent bending stiffness of the test wire;

[0030] The neural network prediction model is obtained by training the physical parameter data of the test wire as the input sample of the input layer of the BP neural network model and the equivalent bending stiffness data of the test wire as the output sample of the output layer of the BP neural network model.

[0031] Preferably, the determining module includes:

[0032] A first determining unit, configured to determine the damping power of the self-damping wire according to the equivalent bending stiffness of the self-damping wire;

[0033] The second determining unit is used to determine the damping coefficient of the self-damping wire according to the damping power of the self-damping wire.

[0034] Further, the first determining unit is used for:

[0035] The damping power P of the self-damping conductor is determined by the following formula: c :

[0036]

[0037] Where m is the mass per unit length of the self-damping conductor; L is the length of the self-damping conductor; T is the tension of the self-damping conductor; V c is the self-damping conductor wave velocity; n is the nth order wavelength of the self-damping conductor; ω n is the nth order circular frequency of the self-damping wire; D is the diameter of the self-damping wire; k D is the equivalent diameter coefficient; EI is the equivalent bending stiffness of the self-damping conductor; parameter K0 = 0.001 ~ 0.006, parameter β0 = -0.2 ~ -0.8; f n is the nth-order frequency of the self-damping conductor; A is the single amplitude of the self-damping conductor.

[0038] Furthermore, the second determining unit is used for:

[0039] The damping coefficient c of the self-damping conductor is determined as follows:

[0040]

[0041] Furthermore, the number of nodes in the hidden layer of the BP neural network model is 8 to 12.

[0042] Compared with the closest prior art, the technical solution provided by the present invention has the following excellent effects:

[0043] The present invention provides a method and device for determining the self-damping coefficient of a self-damping conductor. A neural network prediction model is established through experimental data, and the physical parameters of the self-damping conductor are input into the pre-established neural network prediction model to obtain the bending stiffness of the self-damping conductor, thereby saving the test time and test economic cost of the self-damping conductor test, and being more economical. The damping coefficient of the self-damping conductor is determined according to the bending stiffness of the self-damping conductor, and a method for determining the self-damping coefficient is provided, thereby solving the problem of calculating the self-damping coefficient in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flow chart of the method for determining the self-damping coefficient of the present invention;

[0045] Figure 2 It is a schematic diagram of a self-damping coefficient determination device of the present invention;

[0046] Figure 3 It is a schematic diagram of the structure of a neural network prediction model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The invention will be further described in detail below in conjunction with the embodiments.

[0048] like Figure 1 As shown, the present invention provides a method for determining the damping coefficient of a self-damping conductor, the method comprising:

[0049] Step 1: inputting the physical parameters of the self-damping wire into a pre-established neural network prediction model to obtain the equivalent bending stiffness of the self-damping wire;

[0050] Step 2: determining the damping coefficient of the self-damping wire according to the equivalent bending stiffness of the self-damping wire;

[0051] The process of obtaining the pre-established neural network prediction model in step 1 includes:

[0052] 1) Determination of physical parameters:

[0053] When the tension of the self-damping conductor is zero, the moment of inertia of the cross section of the self-damping conductor is the algebraic sum of the moments of inertia of each strand of the self-damping conductor. The strand calculation method assumes that there is no friction between the strands, that is, each strand is bent separately. The lower limit of the bending stiffness of the self-damping conductor EI is obtained using the following formula: min :

[0054]

[0055] In the formula, E iis the elastic modulus of the i-th conductor in the self-damping conductor; d i is the diameter of the i-th wire in the self-damping wire; q is the total number of wires in the self-damping wire.

[0056] The disadvantage of the strand calculation method is that it does not take into account the internal overhead wire structure of the self-damping conductor, especially the twisting friction between each layer of strands. When the overhead wire is under great stress (tension T = ∞), the overall assumption calculation method assumes that the strands of each layer of the overhead wire are "welded" to each other, that is, the same layer of wires forms a solid structure. The upper limit value of the bending stiffness value of the self-damping conductor EI is obtained using the following formula: max :

[0057]

[0058] In the formula, a i It is the vertical distance from the neutral axis of the damping conductor to the center of the cross section of the i-th conductor.

[0059] In actual engineering, when the self-damping conductor is subjected to a certain tension, the bonding effect between the strands of the self-damping conductor cannot be ignored, and the bending stiffness value obtained by the overall calculation method is too large.

[0060] In this technical solution, by using the following breeze vibration equation

[0061]

[0062] Derived the nth order circular frequency ω of the self-damping conductor n Calculation formula:

[0063]

[0064] According to the formula of the nth order wavelength of the wire The n-order frequency formula of the conductor can be obtained:

[0065]

[0066] Where m is the mass per unit length of the self-damping conductor; L is the length of the self-damping conductor; EI is the equivalent bending stiffness of the self-damping conductor.

[0067] It can be seen that the bending stiffness of the self-damping wire is related to the frequency, tension, wavelength, and mass per unit length. Therefore, the physical parameters are determined as: the diameter, tension, frequency, elastic modulus, and wire gap of the self-damping wire.

[0068] 2) Design of input and output layers

[0069] The parameters of the input layer of the self-damping conductor bending stiffness prediction model are the diameter, tension, frequency, elastic modulus and strand gap of the self-damping conductor, and the output layer is the equivalent bending stiffness EI of the self-damping conductor. The sample data acquisition of the equivalent bending stiffness EI includes:

[0070] The lower limit value EI of the bending stiffness of the self-damping conductor is obtained from the bending stiffness sample data of each frequency in the self-damping conductor bending stiffness test. min and upper limit EI max Sample data of bending stiffness within the range;

[0071] The lower limit of the bending stiffness of the self-damping conductor EI min and upper limit EI max The equivalent bending stiffness of the self-damping wire is obtained by processing the bending stiffness sample data within the range.

[0072] Since the data input into the BP neural network are all positive values, Sigmoid is selected as the transfer function to normalize the input and output of the training set to between [0,1].

[0073] 3) Design of hidden layer

[0074] Under the given step size, learning rate and number of loop steps, different numbers of hidden layer nodes are taken for comparison. The experiment found that the error of the system with (8 to 12) nodes in the hidden layer is the smallest. Figure 3 In the schematic diagram of the neural network prediction model structure of the embodiment of the present invention, the number of nodes in the hidden layer of the BP neural network model can be 8.

[0075] 4) Set learning parameters

[0076] The learning rate was set to 0.001-0.002, and the training target was set to 0.001-0.1. In order to achieve the set training target, the number of network training and the maximum number of failures were set to 10,000-20,000 times. Then, the training error decline curve was observed during the BP neural network training process, and the training was manually stopped after the set target was reached.

[0077] The mapping relationship between the input layer and the output layer is expressed as:

[0078]

[0079] Wherein, δ is the logarithmic sigmoid function; NI, NJ, NK are the number of nodes in the input layer, hidden layer and output layer of the neural network prediction model respectively; in this embodiment, NI = 5, NJ = 8, NK = 1; i, j, k are the i-th, j-th, k-th nodes in the input layer, hidden layer and output layer respectively; w ij 、v jkare the connection weights of the i-th node in the input layer and the j-th node in the hidden layer, and the j-th node in the hidden layer and the k-th node in the output layer respectively; b k , b j are the thresholds of the kth node in the output layer and the jth node in the hidden layer of the neural network prediction model respectively; EI0 is the equivalent bending stiffness sample value obtained from the bending stiffness test of the self-damping wire.

[0080] Step 2 is as follows:

[0081] Step 2-1, determining the damping power of the self-damping wire according to the equivalent bending stiffness of the self-damping wire;

[0082] The damping power calculation formula is obtained as follows:

[0083] Considering the vibration of the damping line under the action of external force, the vibration differential equation is:

[0084]

[0085] Where EI is the equivalent bending stiffness of the self-damping conductor; T is the tension of the self-damping conductor; y is the vertical displacement of the self-damping conductor at position x at time t; F(x,t) is the breeze excitation received by the self-damping conductor at position x at time t; m is the mass per unit length of the self-damping conductor; and c is the damping coefficient of the self-damping conductor.

[0086] Multiply both sides of the above equation by The following equation is obtained:

[0087]

[0088] The left side of the equation is the power dissipated by the vibration wavelength of the conductor in one cycle, and the right side is the power input to the conductor by the wind in one cycle.

[0089] The damping power of the conductor is obtained according to the right side of the equation:

[0090]

[0091] The damping power of the self-damping conductor of the present application is calculated using the above damping power formula:

[0092] Self-damping ratio

[0093] Substituting the self-damping ratio calculation formula into the following damping power P c The calculation formula is:

[0094]

[0095] Where m is the mass per unit length of the self-damping conductor; L is the length of the self-damping conductor; T is the tension of the self-damping conductor; V is the wave velocity of the self-damping conductor; λ n is the nth order wavelength of the self-damping conductor; ω n is the nth order circular frequency of the self-damping wire; D is the diameter of the self-damping wire; k D is the equivalent diameter coefficient, ranging from 0.1 to 0.9; EI is the equivalent bending stiffness of the self-damping conductor; parameter K0 = 0.001 to 0.006, parameter β0 = -0.2 to -0.8.

[0096] The value ranges of parameters K0 and β0 are determined by experimental data.

[0097] Step 2-2, determining the damping coefficient of the self-damping wire according to the damping power of the self-damping wire, comprises:

[0098] The vertical displacement function of the self-damping conductor position x from the equilibrium position at time t is:

[0099]

[0100] Where A is the single amplitude of the self-damped conductor, and τ is the vibration period;

[0101] For a complete wavelength single degree of freedom system of a self-damping conductor under simple harmonic load, the energy W1 consumed by the damping force in one vibration cycle is:

[0102]

[0103] The energy consumed W1 and the energy consumed by the self-damping of an overhead wire of one wavelength in one cycle W2 = P c λ n τ is equivalent to,

[0104] Let W1 = W2, according to The calculation formula of the damping coefficient c of the damping wire can be obtained:

[0105]

[0106] Where P c is the damping power of the self-damping conductor; A is the single amplitude of the self-damping conductor; f n is the nth-order frequency of the self-damping conductor.

[0107] The two parameters of equivalent bending stiffness and damping coefficient determined by the technical solution of the present application are substituted into the finite element model for harmonic response calculation to obtain the antinode amplitude at the wire clamp outlet. It can be seen from Table 1 that the calculated value and the experimental value of the antinode amplitude at the wire clamp outlet are consistent with each other, thereby verifying that the damping coefficient determination method of the present application is correct.

[0108] Table 1 Test and calculated values ​​of antinode amplitude of self-damping conductor

[0109] Frequency / Hz Antinode amplitude test value / mm Frequency / Hz Calculated value of antinode amplitude / mm 16.13 25.96 16.58 26.58 21.65 14.80 20.46 15.13 25.48 11.44 25.72 12.21 30.71 7.73 29.77 8.18

[0110] like Figure 2 As shown, the present invention provides a device for determining the damping coefficient of a self-damping conductor, the device comprising:

[0111] A prediction module, used for inputting the physical parameters of the self-damping wire into a pre-established neural network prediction model to obtain the equivalent bending stiffness of the self-damping wire;

[0112] A determination module, used to determine the damping coefficient of the self-damping wire according to the equivalent bending stiffness of the self-damping wire;

[0113] The physical parameters include: frequency, tension, wavelength and mass per unit length of the self-damping conductor.

[0114] The process of acquiring a pre-built neural network prediction model includes:

[0115] Performing a bending stiffness test experiment on the test wire to obtain the equivalent bending stiffness of the test wire;

[0116] The neural network prediction model is obtained by training the physical parameter data of the test wire as the input sample of the input layer of the BP neural network model and the equivalent bending stiffness data of the test wire as the output sample of the output layer of the BP neural network model.

[0117] The determination module includes:

[0118] A first determining unit, configured to determine the damping power of the self-damping wire according to the equivalent bending stiffness of the self-damping wire;

[0119] The second determining unit is used to determine the damping coefficient of the self-damping wire according to the damping power of the self-damping wire.

[0120] The first determining unit in the determining module is specifically used for:

[0121] The damping power P of the self-damping conductor is determined by the following formula: c :

[0122]

[0123] Where m is the mass per unit length of the self-damping conductor; L is the length of the self-damping conductor; T is the tension of the self-damping conductor; V c is the self-damping conductor wave velocity; n is the nth order wavelength of the self-damping conductor; ω n is the nth order circular frequency of the self-damping wire; D is the diameter of the self-damping wire; k Dis the equivalent diameter coefficient; EI is the equivalent bending stiffness of the self-damping conductor; parameter K0 = 0.001 ~ 0.006, parameter β0 = -0.2 ~ -0.8; A is the single amplitude of the self-damping conductor; f n is the nth-order frequency of the self-damping conductor.

[0124] The number of nodes in the hidden layer of the input layer of the BP neural network model is 8 to 12.

[0125] The second determining unit in the determining module is specifically used for:

[0126] The damping coefficient c of the self-damping conductor is determined as follows:

[0127]

[0128] In summary, the present invention provides a method and device for determining the self-damping coefficient of a self-damping conductor, establishes a neural network prediction model through experimental data, inputs the physical parameters of the self-damping conductor into the pre-established neural network prediction model to obtain the bending stiffness of the self-damping conductor, saves the test time and test economic cost of the self-damping conductor test, and is more economical; the damping coefficient of the self-damping conductor is determined according to the bending stiffness of the self-damping conductor, and a method for determining the self-damping coefficient is given, which solves the calculation problem of the self-damping coefficient in the prior art.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although ordinary technicians in the relevant field refer to the above embodiments, they should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention are within the scope of protection of the claims of the present invention to be approved.

[0130] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0131] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0134] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art can still modify or make equivalent substitutions to the specific implementations of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention are within the scope of protection of the claims of the present invention to be approved.

Claims

1. A method for determining the damping coefficient of a self-damping conductor, characterized in that: The method comprises: Inputting the physical parameters of the self-damping wire into a pre-established neural network prediction model to obtain the equivalent bending stiffness of the self-damping wire; Determining a damping coefficient of the self-damping wire according to the equivalent bending stiffness of the self-damping wire; Wherein, the physical parameters include: diameter, tension, frequency, elastic modulus and strand gap of the self-damping conductor; The obtaining of the damping coefficient of the self-damping wire according to the equivalent bending stiffness of the self-damping wire comprises: Determining the damping power of the self-damping wire according to the equivalent bending stiffness of the self-damping wire; Determining a damping coefficient of the self-damping wire according to the damping power of the self-damping wire; Determining the damping power of the self-damping wire according to the equivalent bending stiffness of the self-damping wire comprises: The damping power P of the self-damping conductor is determined by the following formula: c : Where m is the mass per unit length of the self-damping conductor; L is the length of the self-damping conductor; T is the tension of the self-damping conductor; V c is the self-damping conductor wave velocity; n is the nth order wavelength of the self-damping conductor; ω n is the nth order circular frequency of the self-damping wire; D is the diameter of the self-damping wire; k D is the equivalent diameter coefficient; EI is the equivalent bending stiffness of the self-damping conductor; parameter K0 = 0.001 ~ 0.006, parameter β0 = -0.2 ~ -0.8; f n is the nth-order frequency of the self-damping conductor; A is the single amplitude of the self-damping conductor.

2. The method according to claim 1, characterized in that The acquisition process of the pre-established neural network prediction model includes: Performing a bending stiffness test experiment on the test wire to obtain the equivalent bending stiffness of the test wire; The neural network prediction model is obtained by training the physical parameter data of the test wire as the input sample of the input layer of the BP neural network model and the equivalent bending stiffness data of the test wire as the output sample of the output layer of the BP neural network model.

3. The method according to claim 1, characterized in that Determining the damping coefficient of the self-damping wire according to the damping power of the self-damping wire comprises: The damping coefficient c of the self-damping conductor is determined as follows: In the formula, A 2 is the square of the single amplitude of the self-damped conductor; is the square of the nth-order frequency of the self-damped conductor.

4. The method according to claim 2, characterized in that The number of nodes in the hidden layer of the BP neural network model is 8 to 12.

5. A device for determining the damping coefficient of a self-damping conductor, characterized in that: The device comprises: A prediction module, used for inputting the physical parameters of the self-damping wire into a pre-established neural network prediction model to obtain the equivalent bending stiffness of the self-damping wire; A determination module, used to determine the damping coefficient of the self-damping wire according to the equivalent bending stiffness of the self-damping wire; Wherein, the physical parameters include: diameter, tension, frequency, elastic modulus and strand gap of the self-damping conductor; The determination module comprises: A first determining unit, configured to determine the damping power of the self-damping wire according to the equivalent bending stiffness of the self-damping wire; A second determining unit, configured to determine a damping coefficient of the self-damping wire according to the damping power of the self-damping wire; The first determining unit is used for: The damping power P of the self-damping conductor is determined by the following formula: c : Where m is the mass per unit length of the self-damping conductor; L is the length of the self-damping conductor; T is the tension of the self-damping conductor; V c is the self-damping conductor wave velocity; n is the nth order wavelength of the self-damping conductor; ω n is the nth order circular frequency of the self-damping wire; D is the diameter of the self-damping wire; k D is the equivalent diameter coefficient; EI is the equivalent bending stiffness of the self-damping conductor; parameter K0 = 0.001 ~ 0.006, parameter β0 = -0.2 ~ -0.8; f n is the nth-order frequency of the self-damping conductor; A is the single amplitude of the self-damping conductor.

6. The device according to claim 5, characterized in that The acquisition process of the pre-established neural network prediction model includes: Performing a bending stiffness test experiment on the test wire to obtain the equivalent bending stiffness of the test wire; The neural network prediction model is obtained by training the physical parameter data of the test wire as the input sample of the input layer of the BP neural network model and the equivalent bending stiffness data of the test wire as the output sample of the output layer of the BP neural network model.

7. The device according to claim 5, characterized in that The second determining unit is used for: The damping coefficient c of the self-damping conductor is determined as follows: Where A2 is the square of the single amplitude of the self-damping conductor; is the square of the nth-order frequency of the self-damped conductor.

8. The device according to claim 6, characterized in that The number of nodes in the hidden layer of the input layer of the BP neural network model is 8 to 12.

Images