Pumped storage counterweight optimization method and equipment and storage medium

Abstract

The invention discloses a pumped storage counterweight optimization method and device and a storage medium, and the method comprises the steps: reading a vibration signal collected by a vibration meter for a rotor when the rotor rotates; separating an initial amplitude and an initial phase from the rotor in the vibration signal; calculating a credible coefficient of the vibration meter according to the initial amplitude and the initial phase; on the basis of the initial amplitude and the initial phase, setting a reference amplitude and a reference phase for the rotor according to the credible coefficient; performing optimization operation on the reference amplitude and the reference phase according to the residual vibration of the rotor to obtain a target amplitude and a target phase; and carrying out counterweight on the rotor according to the target amplitude and the target phase. According to the embodiment of the invention, modeling is carried out through the residual vibration of the rotor, an optimal counterweight scheme can be quickly solved, the number of manual experiments is effectively reduced, the experiment period is greatly shortened, and the rotor counterweight efficiency of the pumped storage power station is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pumped storage power stations, and in particular to a pumped storage counterweight optimization method, equipment and storage medium. Background Art

[0002] When the grid load is low, the pumped-storage power station uses excess electricity to pump water from the lower reservoir to the upper reservoir for storage, converting the electricity into gravitational potential energy of the water.

[0003] The rotor in a water pump usually produces unbalanced vibration during operation. In order to improve the working efficiency and life of the water pump, the rotor of the water pump will be subjected to dynamic balancing analysis and counterweight experiments.

[0004] At present, dynamic balancing analysis and counterweight experiments are mostly carried out by technicians relying on manual experience and repeated experiments. The experimental process is cumbersome and the cycle is long. Under conditions of high rotor speed or high vibration, dynamic balancing analysis and counterweight experiments are more difficult. Summary of the invention

[0005] In view of this, the present invention provides a pumped storage counterweight optimization method, device and storage medium to improve the efficiency of the rotor counterweight of a pumped storage power station.

[0006] A first aspect of the present invention provides a pumped storage counterweight optimization method, which is applied to a pumped storage power station, wherein a rotor of a pump in the pumped storage power station is provided with a vibration meter, and the method comprises:

[0007] When the rotor rotates, reading the vibration signal collected by the vibration meter from the rotor;

[0008] Separating an initial amplitude and an initial phase of the rotor from the vibration signal;

[0009] Calculating a credibility coefficient for the vibrometer according to the initial amplitude and the initial phase;

[0010] On the basis of the initial amplitude and the initial phase, setting a reference amplitude and a reference phase for the rotor according to the credibility coefficient;

[0011] performing an optimization operation on the reference amplitude and the reference phase according to the residual vibration of the rotor to obtain a target amplitude and a target phase;

[0012] The rotor is weighted according to the target amplitude and the target phase.

[0013] Optionally, calculating a credibility coefficient of the vibrometer according to the initial amplitude and the initial phase includes:

[0014] Calculating a first average value for the initial amplitude, calculating a first standard deviation for the initial amplitude according to the first average value, and amplifying the first standard deviation to a first threshold value;

[0015] Calculating a second average value for the initial phase, calculating a second standard deviation for the initial phase according to the second average value, and amplifying the second standard deviation to a second threshold value;

[0016] If the difference between the initial amplitude and the first average value is smaller than the first threshold, and the difference between the initial phase and the second average value is smaller than the second threshold, determining that the credibility coefficient of the vibrometer is a first value;

[0017] If the difference between the initial amplitude and the first average value is greater than or equal to the first threshold, or the difference between the initial phase and the second average value is greater than or equal to the second threshold, the credibility coefficient of the vibrometer is determined to be a second value.

[0018] Optionally, calculating a first standard deviation of the initial amplitude according to the first average value includes:

[0019] The first standard deviation is calculated for the initial amplitude according to the first average value by the following formula:

[0020]

[0021] Wherein, σ1 is the first standard deviation, μ1 is the first mean value, n is the number, V ci is the swing amplitude characteristic value of the i-th vibration signal;

[0022] The calculating a second standard deviation of the initial phase according to the second average value comprises:

[0023] The second standard deviation of the initial phase is calculated according to the second average value by the following formula:

[0024]

[0025] Where σ2 is the second standard deviation, μ2 is the second mean, n is the number, P ci The oscillation phase characteristic value of the i-th vibration signal.

[0026] Optionally, the step of setting a reference amplitude and a reference phase for the rotor based on the initial amplitude and the initial phase according to the credibility coefficient includes:

[0027] On the basis of the initial amplitude and the initial phase, the reference amplitude and the reference phase are set for the rotor according to the credibility coefficient by the following formula:

[0028]

[0029] Wherein, V0 is the reference amplitude, P0 is the reference phase, n is the number, t i is the ith credibility coefficient, V 0i is the initial amplitude of the ith 0i is the i-th initial phase.

[0030] Optionally, performing an optimization operation on the reference amplitude and the reference phase according to the residual vibration of the rotor to obtain a target amplitude and a target phase includes:

[0031] Calculating an original residual vibration value of the rotor using the reference amplitude and the reference phase;

[0032] Performing a normalization operation on the original residual vibration value to obtain a target residual vibration value;

[0033] constructing an objective function according to the target residual vibration value;

[0034] A gradient descent operation is performed on the objective function to minimize the objective function when the reference amplitude is optimized to the target amplitude and the reference phase is optimized to the target phase.

[0035] Optionally, the original residual vibration value is expressed as:

[0036] R i =((V Ii *V*Cos(Rad(P Ii +P))+V ci *Cos(Rad(P ci ))) 2

[0037] +(V Ii *V*Sin(Rad(P Ii +P))+V ci *Sin(Rad(P ci ))) 2 ) 1 / 2

[0038] Among them, R i is the i-th original residual vibration value, V is the reference amplitude, P is the reference phase, V Ii is the i-th first influence coefficient, P Ii is the ith second influence coefficient, V ci is the swing amplitude characteristic value of the i-th vibration signal, P ciis the oscillation phase characteristic value of the i-th vibration signal, Cos is the cosine function, Sin is the sine function, and Rad is radians.

[0039] Optionally, the normalization operation is expressed as:

[0040] R vi =R i *Z i

[0041] Among them, R i is the original residual vibration value of the ith i is the ith normalization coefficient, R vi is the i-th target residual vibration value.

[0042] Optionally, the objective function is expressed as:

[0043]

[0044] Wherein, L(L,P) is the objective function, m is the residual vibration balance coefficient, n is the number, t i is the ith credibility coefficient, R vi is the ith target residual vibration value, and Max is the maximum value function.

[0045] A second aspect of the present invention provides a pumped storage counterweight optimization device, which is applied to a pumped storage power station, wherein the rotor of a pump in the pumped storage power station is provided with a vibration meter, and the device comprises:

[0046] A vibration signal reading module, used for reading the vibration signal collected by the vibration meter from the rotor when the rotor rotates;

[0047] A vibration signal separation module, used for separating an initial amplitude and an initial phase of the rotor from the vibration signal;

[0048] A credibility coefficient calculation module, used for calculating a credibility coefficient of the vibrometer according to the initial amplitude and the initial phase;

[0049] A reference setting module, configured to set a reference amplitude and a reference phase for the rotor based on the initial amplitude and the initial phase and according to the credibility coefficient;

[0050] A target optimization module, configured to perform an optimization operation on the reference amplitude and the reference phase according to the residual vibration of the rotor to obtain a target amplitude and a target phase;

[0051] A rotor weighting module is used to balance the rotor according to the target amplitude and the target phase.

[0052] Optionally, the credibility coefficient calculation module includes:

[0053] an initial amplitude processing module, configured to calculate a first average value for the initial amplitude, calculate a first standard deviation for the initial amplitude according to the first average value, and amplify the first standard deviation to a first threshold value;

[0054] an initial phase processing module, configured to calculate a second average value for the initial phase, calculate a second standard deviation for the initial phase according to the second average value, and amplify the second standard deviation to a second threshold value;

[0055] a first coefficient determination module, configured to determine that the credibility coefficient of the vibrometer is a first value if the difference between the initial amplitude and the first average value is less than the first threshold value, and the difference between the initial phase and the second average value is less than the second threshold value;

[0056] The second coefficient determination module is used to determine that the credibility coefficient of the vibrometer is a second value if the difference between the initial amplitude and the first average value is greater than or equal to the first threshold, or the difference between the initial phase and the second average value is greater than or equal to the second threshold.

[0057] Optionally, the initial phase processing module includes:

[0058] The first standard deviation calculation module is used to calculate the first standard deviation of the initial amplitude according to the first average value by using the following formula:

[0059]

[0060] Wherein, σ1 is the first standard deviation, μ1 is the first mean value, n is the number, V ci is the swing amplitude characteristic value of the i-th vibration signal;

[0061] The initial phase processing module comprises:

[0062] The second standard deviation calculation module is used to calculate the second standard deviation of the initial phase according to the second average value by using the following formula:

[0063]

[0064] Where σ2 is the second standard deviation, μ2 is the second mean, n is the number, P ci The oscillation phase characteristic value of the i-th vibration signal.

[0065] Optionally, the benchmark setting module includes:

[0066] A coefficient fusion module is used to set a reference amplitude and a reference phase for the rotor based on the initial amplitude and the initial phase according to the credibility coefficient by using the following formula:

[0067]

[0068] Wherein, V0 is the reference amplitude, P0 is the reference phase, n is the number, t i is the ith credibility coefficient, V 0i is the initial amplitude of the ith 0i is the i-th initial phase.

[0069] Optionally, the target optimization module includes:

[0070] A residual vibration value calculation module, used to calculate an original residual vibration value of the rotor using the reference amplitude and the reference phase;

[0071] A normalization module, used for performing a normalization operation on the original residual vibration value to obtain a target residual vibration value;

[0072] An objective function construction module, used to construct an objective function according to the target residual vibration value;

[0073] A gradient descent module is used to perform a gradient descent operation on the objective function to minimize the objective function when the reference amplitude is optimized to the target amplitude and the reference phase is optimized to the target phase.

[0074] Optionally, the original residual vibration value is expressed as:

[0075] R i =((V Ii *V*Cos(Rad(P Ii +P))+V ci *Cos(Rad(P ci ))) 2

[0076] +(V Ii *V*Sin(Rad(P Ii +P))+V ci *Sin(Rad(P ci ))) 2 ) 1 / 2

[0077] Among them, R i is the i-th original residual vibration value, V is the reference amplitude, P is the reference phase, V Ii is the i-th first influence coefficient, P Ii is the ith second influence coefficient, Vci is the swing amplitude characteristic value of the i-th vibration signal, P ci is the oscillation phase characteristic value of the i-th vibration signal, Cos is the cosine function, Sin is the sine function, and Rad is radians.

[0078] Optionally, the normalization operation is expressed as:

[0079] R vi =R i *Z i

[0080] Among them, R i is the original residual vibration value of the ith i is the ith normalization coefficient, R vi is the ith target residual vibration value.

[0081] Optionally, the objective function is expressed as:

[0082]

[0083] Wherein, L(L,P) is the objective function, m is the residual vibration balance coefficient, n is the number, t i is the ith credibility coefficient, R vi is the ith target residual vibration value, and Max is the maximum value function.

[0084] A third aspect of the present invention provides an electronic device, the electronic device comprising:

[0085] at least one processor; and

[0086] a memory communicatively connected to the at least one processor; wherein,

[0087] The memory stores a computer program that can be executed 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 pumped storage power balance weight optimization method as described in the first aspect above.

[0088] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the pumped storage counterweight optimization method as described in the first aspect above.

[0089] A fifth aspect of the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the pumped storage power counterweight optimization method as described in the first aspect above.

[0090] In this embodiment, when the rotor rotates, the vibration signal collected by the vibration meter on the rotor is read; the initial amplitude and initial phase of the rotor are separated from the vibration signal; the credibility coefficient of the vibration meter is calculated based on the initial amplitude and initial phase; on the basis of the initial amplitude and initial phase, the reference amplitude and reference phase are set for the rotor according to the credibility coefficient; the reference amplitude and reference phase are optimized according to the residual vibration of the rotor to obtain the target amplitude and target phase; the rotor is weighted according to the target amplitude and target phase. This embodiment can quickly solve the optimal weighting scheme by modeling the residual vibration of the rotor, effectively reducing the number of manual experiments and greatly reducing the experimental cycle, thereby improving the efficiency of rotor weighting of pumped storage power stations.

[0091] 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

[0092] 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.

[0093] Figure 1 It is a flow chart of a pumped storage counterweight optimization method provided in Example 1 of the present invention.

[0094] Figure 2 This is an architecture diagram of an intelligent optimization platform provided in Example 1 of the present invention.

[0095] Figure 3 It is a structural schematic diagram of a pumped storage counterweight optimization device provided in Example 2 of the present invention.

[0096] Figure 4 It is a structural schematic diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0097] 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.

[0098] 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 interchangeable where appropriate, so that the embodiments of the present invention described herein can cover sequential implementations 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.

[0099] Embodiment 1

[0100] See also Figure 1 , shows a flow chart of a pumped storage counterweight optimization method provided by the first embodiment of the present invention, the method can be executed by a pumped storage counterweight optimization device, the pumped storage counterweight optimization device can be implemented in the form of hardware and / or software, and the pumped storage counterweight optimization device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0101] Step 101: When the rotor rotates, read the vibration signal collected by the vibration meter on the rotor.

[0102] like Figure 2 As shown, this embodiment can be applied to a pumped storage power station, especially an intelligent optimization platform of a pumped storage power station, wherein the rotor of a water pump in the pumped storage power station is provided with a vibration meter (sensor).

[0103] When the rotor of the water pump is running and rotating, the vibration meter continuously collects vibration signals from the rotor and transmits the vibration signals to the intelligent optimization platform. When the intelligent optimization platform receives the vibration signals collected by the vibration meter on the rotor, it automatically performs dynamic balancing analysis and counterweight experiments.

[0104] Step 102: Separate the initial amplitude and initial phase of the rotor from the vibration signal.

[0105] In this embodiment, the vibration signal can be converted from the time domain to the frequency domain using algorithms such as FFT (Fast Fourier Transform). In the frequency domain, the vibration signal is separated from the rotor to obtain an initial amplitude (with an accuracy of 0.1) and an initial phase (with an accuracy of 1.0).

[0106] Step 103: Calculate the credibility coefficient of the vibrometer according to the initial amplitude and the initial phase.

[0107] In practical applications, the vibration meter will have certain errors. In order to prevent the measurement error of individual vibration meters from being large and causing weight errors, the credibility coefficient of the vibration meter when measuring vibration signals can be comprehensively measured from the two aspects of initial amplitude and initial phase, thereby characterizing the error of the vibration meter to a certain extent and reducing the contribution of this error direction to the weight.

[0108] In one embodiment of the present invention, step 103 may include the following steps:

[0109] Step 1031: Calculate a first average value for the initial amplitude, calculate a first standard deviation for the initial amplitude based on the first average value, and amplify the first standard deviation to a first threshold value.

[0110] In this embodiment, the first average value can be calculated from the initial amplitude using the following formula:

[0111]

[0112] Where μ1 is the first average value, n is the number of vibrometers, V oi is the initial amplitude of the i-th vibration signal.

[0113] Furthermore, the first standard deviation is calculated for the initial amplitude according to the first average value by the following formula:

[0114]

[0115] Where σ1 is the first standard deviation, μ1 is the first mean, n is the number of vibrometers, V ci is the swing amplitude characteristic value of the i-th vibration signal (that is, the amplitude of the vibration signal characterizing the swing characteristic).

[0116] Then, the product of the first standard deviation and a preset first amplification factor (the first amplification factor is greater than or equal to 1, such as 3) is calculated as the first threshold.

[0117] Step 1032: Calculate a second average value for the initial phase, calculate a second standard deviation for the initial phase based on the second average value, and amplify the second standard deviation to a second threshold value.

[0118] In this embodiment, the second average value can be calculated for the initial phase using the following formula:

[0119]

[0120] Where μ2 is the second average value, n is the number of vibrometers, P oi is the initial phase of the i-th vibration signal.

[0121] Further, the second standard deviation of the initial phase is calculated according to the second average value by the following formula:

[0122]

[0123] Where σ2 is the second standard deviation, μ2 is the second mean, n is the number of vibrometers, P ci The swing phase eigenvalue of the ith vibration signal (i.e., the vibration signal’s phase characteristic of the swing).

[0124] Then, the product of the second standard deviation and a preset second amplification factor (the second amplification factor is greater than or equal to 1, such as 3) is calculated as the second threshold.

[0125] Step 1033: If the difference between the initial amplitude and the first average value is smaller than the first threshold, and the difference between the initial phase and the second average value is smaller than the second threshold, determine that the credibility coefficient of the vibration meter is a first value.

[0126] Step 1034: If the difference between the initial amplitude and the first average value is greater than or equal to the first threshold, or the difference between the initial phase and the second average value is greater than or equal to the second threshold, determine that the credibility coefficient of the vibration meter is a second value.

[0127] In practical applications, the error of most vibrometers when measuring vibration signals is within the allowable range. Then, the degree of outliers of the initial weighting scheme (i.e., initial amplitude, initial phase) calculated in the direction of each vibrometer can reflect the error probability and degree of the vibrometer. Assuming that the difference between this error and the mean of the initial weighting scheme is normally distributed, the credibility coefficient t of the i-th one can be calculated simultaneously as follows: i for:

[0128]

[0129] Among them, l is the first value, k is the second value, w1 is the first amplification coefficient, w2 is the second amplification coefficient, ∩ is the sum, and ∥ is the or.

[0130] Generally, the first value is greater than the second value.

[0131] Step 104: On the basis of the initial amplitude and the initial phase, a reference amplitude and a reference phase are set for the rotor according to a credibility coefficient.

[0132] In this embodiment, the initial amplitude may be fused according to the credibility coefficient to obtain the rotor reference amplitude, and the initial phase may be fused according to the credibility coefficient to obtain the rotor reference phase.

[0133] In the specific implementation, based on the initial amplitude and initial phase, the reference amplitude and reference phase of the rotor are set according to the credibility coefficient through the following formula:

[0134]

[0135] Where V0 is the reference amplitude, P0 is the reference phase, n is the number of vibrometers, t i is the ith credibility coefficient, V 0i is the i-th initial amplitude, P 0i is the i-th initial phase.

[0136] Step 105: Optimize the reference amplitude and the reference phase according to the residual vibration of the rotor to obtain the target amplitude and the target phase.

[0137] In practical applications, the rotor will have residual vibration in a certain direction. With the goal of minimizing the residual vibration, the reference amplitude and the reference phase can be optimized to optimize the reference amplitude to the target amplitude and the reference phase to the target phase.

[0138] In one embodiment of the present invention, step 105 may include the following steps:

[0139] Step 1051: Calculate the original residual vibration value of the rotor using the reference amplitude and the reference phase.

[0140] In this embodiment, the value of the residual vibration of the rotor may be calculated in combination with the reference amplitude and the reference phase, and recorded as the original residual vibration value.

[0141] Exemplarily, the original residual vibration value is expressed as:

[0142] R i =((V Ii *V*Cos(Rad(P Ii +P))+V ci *Cos(Rad(P ci ))) 2

[0143] +(V Ii *V*Sin(Rad(P Ii +P))+V ci *Sin(Rad(P ci ))) 2 ) 1 / 2

[0144] Among them, R i is the i-th original residual vibration value, V is the amplitude parameter to be optimized, the initial value is the reference amplitude, P is the phase parameter to be optimized, the initial value is the reference phase, V Ii is the i-th first influence coefficient (with an accuracy of 0.01), P Ii is the ith second influence coefficient (with an accuracy of 0.1), V ciis the swing amplitude characteristic value of the i-th vibration signal, P ci is the oscillation phase eigenvalue of the i-th vibration signal, Cos is the cosine function, Sin is the sine function, and Rad is radians.

[0145] Step 1052: Perform a normalization operation on the original residual vibration value to obtain a target residual vibration value.

[0146] In this embodiment, a linear or nonlinear method may be used to perform a normalization operation on the original residual vibration value to obtain a target residual vibration value.

[0147] Exemplarily, the normalization operation is expressed as:

[0148] R vi =R i *Z i

[0149] Among them, R i is the i-th original residual vibration value, Z i is the ith normalization coefficient, R vi is the i-th target residual vibration value.

[0150] Step 1053: construct an objective function according to the target residual vibration value.

[0151] In this embodiment, the target residual vibration value is a parameter to be optimized, and an objective function to be optimized can be constructed according to the target residual vibration value.

[0152] Exemplarily, the objective function is expressed as:

[0153]

[0154] Where L(L,P) is the objective function, m is the residual vibration balance coefficient, n is the number of vibration meters, and t i is the ith credibility coefficient, R vi is the i-th target residual vibration value, and Max is the maximum value function.

[0155] In this example, the objective function consists of two parts. The first part is It is calculated by weighting and averaging the target residual vibration value using the credibility coefficient. The second part is It is calculated by using the credibility coefficient to weight the target residual vibration value and find the maximum value.

[0156] This example introduces the residual vibration equalization coefficient m (0≤m≤1), combines the two parts, and obtains the final objective function.

[0157] Generally speaking, technicians can set the residual vibration balancing coefficient based on the actual situation and experience of the pumped-storage power station.

[0158] Furthermore, when m=1, the maximum target residual vibration value is optimized, and when m=0, all target residual vibration values ​​are optimized. At this time, the target residual vibration value in a certain direction may be relatively large.

[0159] Step 1054: perform a gradient descent operation on the objective function to minimize the objective function when the reference amplitude is optimized to the target amplitude and the reference phase is optimized to the target phase.

[0160] In this embodiment, a gradient descent operation may be performed on the objective function, and the reference amplitude and the reference phase may be continuously iterated. When the reference amplitude is optimized to the target amplitude and the reference phase is optimized to the target phase, the output value of the objective function is minimized.

[0161] In the specific implementation, the gradient equation when performing the gradient descent operation on the objective function is:

[0162]

[0163] Among them, Grad represents gradient.

[0164] Based on the objective function, when L takes the partial derivative of V, let a i =V Ii *Cos(Rad(P Ii +P i ), b i =V ci *Cos(Rad(P ci )),c i =V Ii *Sin(Rad(P Ii +P i ))、d i =V ci *Sin(Rad(P ci )).

[0165] At this time, the target residual vibration value can be recorded as R Vi =((a i V i +b i ) 2 +(c i V i +d i ) 2 ) 1 / 2 .

[0166] Then, the partial derivative of L with respect to V is:

[0167]

[0168] Wherein, j is the number of the vibration meter with the largest target residual vibration value.

[0169] On the basis of the objective function, when L is used to find the partial derivative of P, P' = rP Ii +rP, where r = Π / 180, a i =V Ii *V i , b i =V ci *Cos(Rad(P ci )), c i =V ci *Sin(Rad(P ci ).

[0170] At this time, the target residual vibration value can be recorded as R Vi =((a i *Cos(P')+b i ) 2 +(a i *Sin(P'))+c i ) 2 ) 1 / 2 .

[0171] Then, the partial derivative of L with respect to P is:

[0172]

[0173] Wherein, j is the number of the vibration meter with the largest target residual vibration value.

[0174] In each iteration, V and P are updated as follows:

[0175]

[0176] Where n is the nth iteration, n-1 is the n-1th iteration, and e V With e P are learning rates.

[0177] Step 106: Balance the rotor according to the target amplitude and the target phase.

[0178] like Figure 2 As shown, the intelligent optimization platform can control the counterweight device to increase or decrease the pole counterweight blocks for the three phases of the rotor (i.e., phase A, phase B, and phase C) according to the target amplitude, so that the target phase adapts to the orbit, realizes automatic counterweighting of the rotor, and optimizes the dynamic balance of the unit.

[0179] In this embodiment, when the rotor rotates, the vibration signal collected by the vibration meter on the rotor is read; the initial amplitude and initial phase of the rotor are separated from the vibration signal; the credibility coefficient of the vibration meter is calculated based on the initial amplitude and initial phase; on the basis of the initial amplitude and initial phase, the reference amplitude and reference phase are set for the rotor according to the credibility coefficient; the reference amplitude and reference phase are optimized according to the residual vibration of the rotor to obtain the target amplitude and target phase; the rotor is weighted according to the target amplitude and target phase. This embodiment can quickly solve the optimal weighting scheme by modeling the residual vibration of the rotor, effectively reducing the number of manual experiments and greatly reducing the experimental cycle, thereby improving the efficiency of rotor weighting of pumped storage power stations.

[0180] Embodiment 2

[0181] See also Figure 3 , showing a schematic diagram of the structure of a pumped storage counterweight optimization device provided by the second embodiment of the present invention. Applied to a pumped storage power station, the rotor of the pump in the pumped storage power station is equipped with a vibration meter, such as Figure 3 As shown, the device comprises:

[0182] A vibration signal reading module 301 is used to read the vibration signal collected by the vibration meter from the rotor when the rotor rotates;

[0183] A vibration signal separation module 302, used to separate an initial amplitude and an initial phase of the rotor from the vibration signal;

[0184] A credibility coefficient calculation module 303, used to calculate a credibility coefficient for the vibrometer according to the initial amplitude and the initial phase;

[0185] A reference setting module 304 is used to set a reference amplitude and a reference phase for the rotor based on the initial amplitude and the initial phase according to the credibility coefficient;

[0186] A target optimization module 305 is used to perform an optimization operation on the reference amplitude and the reference phase according to the residual vibration of the rotor to obtain a target amplitude and a target phase;

[0187] The rotor weighting module 306 is configured to weight the rotor according to the target amplitude and the target phase.

[0188] In one embodiment of the present invention, the credibility coefficient calculation module 303 includes:

[0189] an initial amplitude processing module, configured to calculate a first average value for the initial amplitude, calculate a first standard deviation for the initial amplitude according to the first average value, and amplify the first standard deviation to a first threshold value;

[0190] an initial phase processing module, configured to calculate a second average value for the initial phase, calculate a second standard deviation for the initial phase according to the second average value, and amplify the second standard deviation to a second threshold value;

[0191] a first coefficient determination module, configured to determine that the credibility coefficient of the vibrometer is a first value if the difference between the initial amplitude and the first average value is less than the first threshold value, and the difference between the initial phase and the second average value is less than the second threshold value;

[0192] The second coefficient determination module is used to determine that the credibility coefficient of the vibrometer is a second value if the difference between the initial amplitude and the first average value is greater than or equal to the first threshold, or the difference between the initial phase and the second average value is greater than or equal to the second threshold.

[0193] In one embodiment of the present invention, the initial phase processing module includes:

[0194] The first standard deviation calculation module is used to calculate the first standard deviation of the initial amplitude according to the first average value by using the following formula:

[0195]

[0196] Wherein, σ1 is the first standard deviation, μ1 is the first mean value, n is the number, V ci is the swing amplitude characteristic value of the i-th vibration signal;

[0197] The initial phase processing module comprises:

[0198] The second standard deviation calculation module is used to calculate the second standard deviation of the initial phase according to the second average value by using the following formula:

[0199]

[0200] Where σ2 is the second standard deviation, μ2 is the second mean, n is the number, P ci The oscillation phase characteristic value of the i-th vibration signal.

[0201] In one embodiment of the present invention, the benchmark setting module 304 includes:

[0202] A coefficient fusion module is used to set a reference amplitude and a reference phase for the rotor based on the initial amplitude and the initial phase according to the credibility coefficient by using the following formula:

[0203]

[0204] Wherein, V0 is the reference amplitude, P0 is the reference phase, n is the number, t i is the ith credibility coefficient, V 0i is the initial amplitude of the ith 0i is the i-th initial phase.

[0205] In one embodiment of the present invention, the target optimization module 305 includes:

[0206] A residual vibration value calculation module, used to calculate an original residual vibration value of the rotor using the reference amplitude and the reference phase;

[0207] A normalization module, used for performing a normalization operation on the original residual vibration value to obtain a target residual vibration value;

[0208] An objective function construction module, used to construct an objective function according to the target residual vibration value;

[0209] A gradient descent module is used to perform a gradient descent operation on the objective function to minimize the objective function when the reference amplitude is optimized to the target amplitude and the reference phase is optimized to the target phase.

[0210] In one embodiment of the present invention, the original residual vibration value is expressed as:

[0211] R i =((V Ii *V*Cos(Rad(P Ii +P))+V ci *Cos(Rad(P ci ))) 2

[0212] +(V Ii *V*Sin(Rad(P Ii +P))+V ci *Sin(Rad(P ci ))) 2 ) 1 / 2

[0213] Among them, R i is the i-th original residual vibration value, V is the reference amplitude, P is the reference phase, V Ii is the i-th first influence coefficient, P Ii is the ith second influence coefficient, V ci is the swing amplitude characteristic value of the i-th vibration signal, P ci is the oscillation phase characteristic value of the i-th vibration signal, Cos is the cosine function, Sin is the sine function, and Rad is radians.

[0214] In one embodiment of the present invention, the normalization operation is expressed as:

[0215] R vi =R i *Z i

[0216] Among them, R i is the original residual vibration value of the ith i is the ith normalization coefficient, R vi is the ith target residual vibration value.

[0217] In one embodiment of the present invention, the objective function is expressed as:

[0218]

[0219] Wherein, L(L,P) is the objective function, m is the residual vibration balance coefficient, n is the number, t i is the ith credibility coefficient, R vi is the ith target residual vibration value, and Max is the maximum value function.

[0220] The pumped storage counterweight optimization device provided in the embodiment of the present invention can execute the pumped storage counterweight optimization method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the pumped storage counterweight optimization method.

[0221] Embodiment 3

[0222] See also Figure 4 , shows a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0223] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0224] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0225] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the pumped storage counterweight optimization method.

[0226] In some embodiments, the pumped storage counterweight optimization method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the pumped storage counterweight optimization method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the pumped storage counterweight optimization method in any other appropriate manner (e.g., by means of firmware).

[0227] 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), load 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.

[0228] 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.

[0229] 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 combination 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.

[0230] 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).

[0231] 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.

[0232] 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 services.

[0233] Embodiment 4

[0234] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the pumped storage counterweight optimization method provided in any embodiment of the present invention is implemented.

[0235] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0236] 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.

[0237] 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 pumped storage counterweight optimization method, characterized in that: Applied to a pumped storage power station, the rotor of a water pump in the pumped storage power station is provided with a vibration meter, and the method comprises: When the rotor rotates, reading the vibration signal collected by the vibration meter from the rotor; Separating an initial amplitude and an initial phase of the rotor from the vibration signal; Calculating a credibility coefficient for the vibrometer according to the initial amplitude and the initial phase; On the basis of the initial amplitude and the initial phase, setting a reference amplitude and a reference phase for the rotor according to the credibility coefficient; performing an optimization operation on the reference amplitude and the reference phase according to the residual vibration of the rotor to obtain a target amplitude and a target phase; The rotor is weighted according to the target amplitude and the target phase.

2. The method according to claim 1, characterized in that The calculating of the credibility coefficient of the vibrometer according to the initial amplitude and the initial phase includes: Calculating a first average value for the initial amplitude, calculating a first standard deviation for the initial amplitude according to the first average value, and amplifying the first standard deviation to a first threshold value; Calculating a second average value for the initial phase, calculating a second standard deviation for the initial phase according to the second average value, and amplifying the second standard deviation to a second threshold value; If the difference between the initial amplitude and the first average value is smaller than the first threshold, and the difference between the initial phase and the second average value is smaller than the second threshold, determining that the credibility coefficient of the vibrometer is a first value; If the difference between the initial amplitude and the first average value is greater than or equal to the first threshold, or the difference between the initial phase and the second average value is greater than or equal to the second threshold, the credibility coefficient of the vibrometer is determined to be a second value.

3. The method according to claim 2, characterized in that The calculating a first standard deviation of the initial amplitude according to the first average value comprises: The first standard deviation is calculated for the initial amplitude according to the first average value by the following formula: Wherein, σ1 is the first standard deviation, μ1 is the first mean value, n is the number, V ci is the swing amplitude characteristic value of the i-th vibration signal; The calculating a second standard deviation of the initial phase according to the second average value comprises: The second standard deviation of the initial phase is calculated according to the second average value by the following formula: Where σ2 is the second standard deviation, μ2 is the second mean, n is the number, P ci The oscillation phase characteristic value of the i-th vibration signal.

4. The method according to claim 1, characterized in that: The step of setting a reference amplitude and a reference phase for the rotor based on the initial amplitude and the initial phase according to the credibility coefficient includes: On the basis of the initial amplitude and the initial phase, the reference amplitude and the reference phase are set for the rotor according to the credibility coefficient by the following formula: Wherein, V0 is the reference amplitude, P0 is the reference phase, n is the number, t i is the ith credibility coefficient, V 0i is the initial amplitude of the ith 0i is the i-th initial phase.

5. The method according to any one of claims 1 to 4, characterized in that The performing an optimization operation on the reference amplitude and the reference phase according to the residual vibration of the rotor to obtain a target amplitude and a target phase includes: Calculating an original residual vibration value of the rotor using the reference amplitude and the reference phase; Performing a normalization operation on the original residual vibration value to obtain a target residual vibration value; constructing an objective function according to the target residual vibration value; A gradient descent operation is performed on the objective function to minimize the objective function when the reference amplitude is optimized to the target amplitude and the reference phase is optimized to the target phase.

6. The method according to claim 5, characterized in that The original residual vibration value is expressed as: R i =((V Ii *V*Cos(Rad(P Ii +P))+V ci *Cos(Rad(P ci ))) 2 +(V Ii *V*Sin(Rad(P Ii +P))+V ci *Sin(Rad(P ci ))) 2 ) 1 / 2 Among them, R i is the i-th original residual vibration value, V is the reference amplitude, P is the reference phase, V Ii is the i-th first influence coefficient, P Ii is the ith second influence coefficient, V ci is the swing amplitude characteristic value of the i-th vibration signal, P ci is the oscillation phase characteristic value of the i-th vibration signal, Cos is the cosine function, Sin is the sine function, and Rad is radians.

7. The method according to claim 6, characterized in that The normalization operation is expressed as: R vi =R i *Z i Among them, R i is the original residual vibration value of the ith i is the ith normalization coefficient, R vi is the i-th target residual vibration value.

8. The method according to claim 7, characterized in that The objective function is expressed as: Wherein, L(L,P) is the objective function, m is the residual vibration balance coefficient, n is the number, t i is the ith credibility coefficient, R vi is the ith target residual vibration value, and Max is the maximum value function.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the pumped storage power balance weight optimization method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the pumped storage power counterweight optimization method according to any one of claims 1 to 8 is implemented.

Images