A method, device, equipment and storage medium for calculating the losses of a converter valve

Abstract

The present invention discloses a method, device, equipment and storage medium for calculating the losses of a converter valve. The method includes: inputting the actual parameters of the converter valve as input parameters into a pre-constructed mechanism model, and the output parameter obtained is the initial value of the valve losses of the converter valve; inputting the initial value of the valve losses, the cooling water temperature of the converter valve, the cooling water flow rate and the valve hall temperature as input information into a pre-trained neural network, and the output information obtained is the calculated value of the valve losses of the converter valve. In the above technical solution, first, the initial value of the valve losses is determined according to the actual parameters and the mechanism model of the converter valve, and then the calculated value of the valve losses is determined according to the actual parameters, the initial value of the valve losses and the neural network. The calculated value of the valve losses obtained is closer to the actual valve losses value, providing a relatively accurate engineering reference value for the designers and maintenance personnel of the converter valve.

Description

Technical Field

[0001] The embodiments of the present invention relate to current transmission technology, and particularly to a method, device, equipment and storage medium for calculating the losses of a converter valve. Background Art

[0002] With the development of power electronic devices and the application of renewable energy power generation technologies such as wind power and solar energy, the flexible DC transmission technology has been rapidly developed and applied at home and abroad. The flexible DC transmission system has the advantages of a large number of levels, low harmonic content and low power consumption, and is widely used in high-voltage and high-power DC transmission occasions. The size of the losses in the flexible DC transmission system plays a crucial role in the long-term operating cost and operating performance of the system, and is directly related to the safe, stable and economic operation of the system. The losses of the flexible DC transmission system are composed of a converter valve, a coupling transformer, a valve reactor, a DC reactor and auxiliary equipment, etc., among which the converter valve losses account for more than 60%. Affected by control strategies such as modulation strategies, voltage equalization strategies, circulating current suppression strategies and valve cooling and heat dissipation strategies, it is difficult to accurately calculate the converter valve losses.

[0003] In the prior art, the methods for calculating the losses of flexible DC converter valves at home and abroad are power device loss calculation methods based on analytical expressions. The basic idea is to approximate the nearest level approximation modulation strategy as the PWM modulation strategy. In actual engineering, if the ideal PWM carrier phase-shifted modulation method is used for approximation, there may be large errors. Especially when the topology structure and modulation method of the system become complex, such as the full half-bridge hybrid topology and the system injecting the third harmonic, etc., the working modes of the power modules and the switching timings of the devices will also increase accordingly, and the error of the PWM approximation method will further expand. Moreover, since the instantaneous value calculation of the capacitor voltage is relatively complex, in the existing loss calculation, the method of assuming the capacitor voltage as a constant value is adopted. However, in actual engineering, the capacitor voltage usually fluctuates by about ±10%, which will also have a certain impact on the calculation result of the losses.

[0004] Therefore, there is an urgent need for a method for calculating the losses of a converter valve, which can calculate the losses of the converter valve more accurately. Summary of the Invention

[0005] The present invention provides a method, device, equipment and storage medium for calculating the losses of a converter valve, so as to calculate the losses of the converter valve more accurately and provide relatively accurate engineering reference value for the designers and operation and maintenance personnel of the converter valve and the cooling system where the converter valve is located.

[0006] In a first aspect, the embodiments of the present invention provide a method for calculating the losses of a converter valve, including:

[0007] Taking the actual parameters of the converter valve as input parameters and inputting them into a pre-constructed mechanism model, the output parameter obtained is the initial value of the valve loss of the converter valve;

[0008] Taking the initial value of the valve loss, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information and inputting them into a pre-trained neural network, the output information obtained is the calculated value of the valve loss of the converter valve.

[0009] The technical solution of the embodiment of the present invention provides a method for calculating the loss of a converter valve. The method includes: taking the actual parameters of the converter valve as input parameters and inputting them into a pre-constructed mechanism model, and the output parameter obtained is the initial value of the valve loss of the converter valve; taking the initial value of the valve loss, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information and inputting them into a pre-trained neural network, and the output information obtained is the calculated value of the valve loss of the converter valve. In the above technical solution, first, the initial value of the valve loss is determined according to the actual parameters of the converter valve in the mechanism model, and then the calculated value of the valve loss is determined according to the cooling water temperature, the cooling water flow rate, the valve hall temperature, and the initial value of the valve loss of the converter valve in the neural network. On the basis of determining the initial value of the valve loss by mechanism modeling based on the actual parameters, a neural network is introduced to correct the calculated value of the valve loss based on the on-site measured cooling water temperature, cooling water flow rate, and valve hall temperature. The obtained calculated value of the valve loss is closer to the actual valve loss value, providing a relatively accurate engineering reference value for the designers and maintenance personnel of the converter valve.

[0010] Further, before taking the actual parameters of the converter valve as input parameters and inputting them into a pre-constructed mechanism model, and the output parameter obtained is the initial value of the valve loss of the converter valve, it further includes:

[0011] Determining the conduction loss and the switching loss according to the actual parameters, and constructing the mechanism model based on the conduction loss and the switching loss.

[0012] Further, before taking the initial value of the valve loss, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information and inputting them into a pre-trained neural network, it further includes:

[0013] Constructing an initial network model based on a fully connected network;

[0014] Based on the single variable method, adjusting the network structure and hyperparameters of the initial network model in sequence to obtain a preset network model.

[0015] Further, before taking the initial value of the valve loss, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information and inputting them into a pre-trained neural network, it further includes:

[0016] Obtain the historical cooling water temperature, historical cooling water flow rate, historical valve hall temperature, and historical actual loss value of the converter valve within a historical time period, and obtain the initial value of the historical valve loss of the converter valve within the historical time period through the mechanism model;

[0017] Use the initial value of the historical valve loss, the historical cooling water temperature, the historical cooling water flow rate, the historical valve hall temperature, and the historical actual loss value as training data to perform network training on a preset network model, and calculate the loss function;

[0018] Based on the backpropagation algorithm, perform network optimization until the loss function converges to obtain the neural network.

[0019] Further, before inputting the initial value of the valve loss, the cooling water temperature, the cooling water flow rate, and the valve hall temperature of the converter valve as input information into a pre-trained neural network, it further includes:

[0020] Determine the cooling water temperature, the cooling water flow rate, and the valve hall temperature of the converter valve.

[0021] Further, determining the cooling water temperature of the converter valve includes:

[0022] Based on the inlet valve water temperature and / or the outlet valve water temperature of the converter valve, determine the cooling water temperature.

[0023] Further, it further includes:

[0024] Determine the actual valve loss value according to the cooling water temperature and the cooling water flow rate;

[0025] Compare the actual valve loss value with the calculated valve loss value, and determine the accuracy of the loss calculation according to the comparison result.

[0026] In a second aspect, an embodiment of the present invention further provides a converter valve loss calculation device, including:

[0027] An initial value determination module for valve loss, configured to input the actual parameters of the converter valve as input parameters into a pre-constructed mechanism model, and the output parameter is the initial value of the valve loss of the converter valve;

[0028] A calculated value determination module for valve loss, configured to input the initial value of the valve loss, the cooling water temperature, the cooling water flow rate, and the valve hall temperature of the converter valve as input information into a pre-trained neural network, and the output information is the calculated value of the valve loss of the converter valve.

[0029] In a third aspect, an embodiment of the present invention further provides a computer device, and the device includes:

[0030] At least one processor; and a memory communicatively connected to the at least one processor;

[0031] 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 to enable the at least one processor to execute the commutation valve loss calculation method described in any one of the first aspect.

[0032] In a fourth aspect, an embodiment of the present invention further provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to execute the commutation valve loss calculation method described in any one of the first aspect when executed by a computer processor.

[0033] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions run on a computer, the computer is enabled to execute the commutation valve loss calculation method provided in the first aspect.

[0034] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium. Among them, the computer-readable storage medium may be packaged together with the processor of the commutation valve loss calculation device, or may be separately packaged from the processor of the commutation valve loss calculation device. The present application does not make any limitation in this regard.

[0035] For the descriptions of the second aspect, the third aspect, the fourth aspect, and the fifth aspect in the present application, reference may be made to the detailed description of the first aspect; and for the beneficial effects of the descriptions of the second aspect, the third aspect, the fourth aspect, and the fifth aspect, reference may be made to the beneficial effect analysis of the first aspect, which will not be elaborated here.

[0036] In the present application, the name of the above commutation valve loss calculation device does not constitute a limitation to the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the functions of each device or functional module are similar to those of the present application and fall within the scope of the claims of the present application and their equivalent technologies.

[0037] These aspects or other aspects of the present application will be more clearly understood in the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1Flowchart of a commutation valve loss calculation method provided in Embodiment 1 of the present invention;

[0040] Figure 2 Flowchart of a commutation valve loss calculation method provided in Embodiment 2 of the present invention;

[0041] Figure 3 Flowchart of step 230 in a commutation valve loss calculation method provided in Embodiment 2 of the present invention;

[0042] Figure 4 Structural schematic diagram of a commutation valve loss calculation device provided in Embodiment 3 of the present invention;

[0043] Figure 5 Structural schematic diagram of a computer device provided in Embodiment 4 of the present invention. Detailed implementation manners

[0044] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. Additionally, it should be noted that for the sake of description, only parts related to the present invention are shown in the drawings rather than all structures.

[0045] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone.

[0046] Terms such as "first" and "second" in the description of this application are used to distinguish different objects or different processes for the same object, rather than to describe the specific order of the objects.

[0047] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include other unlisted steps or units, or may optionally further include other steps or units inherent to these processes, methods, products or devices.

[0048] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operations are completed, but there can also be additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, and so on. In addition, in the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0049] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific manner.

[0050] In the description of the present application, unless otherwise specified, "a plurality of" means two or more.

[0051] Embodiment 1

[0052] Figure 1 As shown in the flowchart of a commutation valve loss calculation method provided for Embodiment 1 of the present invention, this embodiment is applicable to situations where relatively accurate commutation valve losses need to be calculated, and this method can be executed by a commutation valve loss calculation device, such as Figure 1 shown, and specifically includes the following steps:

[0053] Step 110: Input the actual parameters of the commutation valve as input parameters into a pre-constructed mechanism model, and the obtained output parameter is the initial value of the valve loss of the commutation valve.

[0054] Among them, the actual parameters can include known parameters and empirical values of uncertain parameters.

[0055] Specifically, after inputting the known parameters determined during the operation of the commutation valve and the empirical values of the uncertain parameters into the mechanism model, the mechanism model can determine the initial value of the valve loss of the commutation valve according to the physical relationship between the actual parameters and the valve loss.

[0056] Since the empirical values are used for the uncertain parameters and there are errors from the actual values, the accuracy of the initial value of the valve loss determined by the mechanism model is not high.

[0057] In the embodiments of the present invention, based on the mechanism model, the initial value of the valve loss of the commutation valve can be determined relatively quickly, and the calculation speed is relatively fast.

[0058] Step 120: Input the initial valve loss value, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information into a pre-trained neural network, and the output information obtained is the calculated valve loss value of the converter valve.

[0059] Among them, the neural network is used to determine an accurate calculated valve loss value.

[0060] Specifically, during the operation of the converter valve, the cooling water temperature, the cooling water flow rate, and the valve hall temperature of the converter valve can be obtained, and the obtained cooling water temperature, cooling water flow rate, and valve hall temperature, as well as the initial valve loss value determined by the mechanism model described above, are input into a pre-trained neural network. The neural network can correct the initial valve loss value based on the cooling water temperature, cooling water flow rate, and valve hall temperature to obtain a calculated valve loss value that is closer to the actual valve loss value, making the calculation result of the valve loss more accurate.

[0061] Embodiment 1 of the present invention provides a method for calculating the loss of a converter valve. The method includes: inputting the actual parameters of the converter valve as input parameters into a pre-constructed mechanism model, and the output parameter obtained is the initial valve loss value of the converter valve; inputting the initial valve loss value, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information into a pre-trained neural network, and the output information obtained is the calculated valve loss value of the converter valve. In the above technical solution, first, the initial valve loss value is determined according to the actual parameters in the mechanism model, and then the calculated valve loss value is determined in the neural network according to the cooling water temperature, cooling water flow rate, valve hall temperature, and initial valve loss value of the converter valve. On the basis of determining the initial valve loss value by mechanism modeling based on actual parameters, a neural network is introduced to correct the calculated valve loss value based on the on-site measured cooling water temperature, cooling water flow rate, and valve hall temperature, and the obtained calculated valve loss value is closer to the actual valve loss value, providing a relatively accurate engineering reference value for the designers and maintenance personnel of the converter valve.

[0062] Embodiment 2

[0063] Figure 2 It is a flowchart of a method for calculating the loss of a converter valve provided in Embodiment 2 of the present invention. This embodiment is a specific implementation based on the above embodiment. As Figure 2 shown, in this embodiment, the method may further include:

[0064] Step 210: Determine the conduction loss and the switching loss according to the actual parameters, and construct the mechanism model based on the conduction loss and the switching loss.

[0065] Among them, valve losses can include conduction losses and switching losses. Conduction losses can include IGBT conduction losses and diode conduction losses. Switching losses can include IGBT turn-on losses, IGBT turn-off losses, diode reverse recovery losses, and necessary switching losses.

[0066] Specifically, the IGBT conduction loss can be determined according to the conduction voltage drop bias, conduction current, and conduction resistance of the IGBT. The diode conduction loss can be determined according to the conduction voltage drop bias, conduction current, and conduction resistance of the diode. Specifically, based on the formula P T (i CE ) = i CE U CE0 + i 2 CE r CE the IGBT conduction loss can be determined, where P T (i CE ) represents the IGBT conduction loss, i CE represents the IGBT conduction current, U CE0 represents the IGBT conduction voltage drop bias, and r CE represents the IGBT conduction resistance; based on the formula P D (i f ) = i f U f0 + i 2 f r f the diode conduction loss can be determined, where P D (i f ) represents the diode conduction loss, i f represents the diode conduction current, U f0 represents the diode conduction voltage drop bias, and r f represents the diode conduction resistance. Among them, U CE0 , U f0 , r CE , r f can be obtained from the conduction voltage - conduction current curve in the device manual.

[0067] According to the arm current signal and the switching status of the sub - modules of the commutation valve, the conduction number and conduction loss of the switching devices of all sub - modules can be accurately calculated. Summing up the conduction losses of all devices can obtain the conduction loss of the commutation valve. Determine the conduction loss of a single arm when the single - arm current is greater than 0 and less than 0, and determine the conduction loss of the commutation valve according to the sum of the conduction losses of the single arm when the single - arm current is greater than 0 and less than 0. Specifically, according to the formula the conduction loss of a single arm when the single - arm current is greater than 0 can be determined. According to the formula Determine the on-state loss of a single bridge arm when the single bridge arm current is less than 0, where P cond1 represents the on-state loss of a single bridge arm when the single bridge arm current is greater than 0, P cond2 represents the on-state loss of a single bridge arm when the single bridge arm current is less than 0, i pa represents the single bridge arm current, T represents the fundamental period, N represents the number of sub-modules in a single bridge arm, n represents the number of currently conducting sub-modules in a single bridge arm, n = round(u pa / U C ), U C represents the single bridge arm voltage, u pa represents the capacitor voltage of the sub-module, t 1 、t 2 and t 3 are the zero-crossing moments of the bridge arm current. Furthermore, the on-state loss P cond of the commutation valve can be determined as P cond1 = 6×(P cond2 + P

[0068] The switching loss includes the necessary switching actions to make the output stepped wave follow the modulation wave and the additional switching actions to prevent the capacitor deviation of each sub-module from being too large. Among them, the additional switching actions are highly random and are the main reason for the inaccurate calculation of valve loss by the mechanism model. The additional switching loss includes IGBT turn-on loss, IGBT turn-off loss, diode turn-on loss, and diode reverse recovery loss. Among them, the diode turn-on loss can be ignored. The IGBT turn-on loss, IGBT turn-off loss, and diode reverse recovery loss can all be obtained by fitting a quadratic function to the loss curve given in the device manual. Among them, the IGBT turn-on loss value curve is E on (i CE ) = k 1 (a 1 i 2 CE + b 1 i CE + c 1 ), the IGBT turn-off loss value curve is E off (i CE ) = k 2 (a 2 i 2 CE + b 2 i CE + c 2 ), and the diode reverse recovery loss value curve is E rec (i f ) = k 3 (a 3 i 2 CE + b 3 iCE +c 3 ), a i , b i , c i , where \(i = 1, 2, 3\) are the coefficients of the quadratic polynomial, and \(k\) i , where \(i = 1, 2, 3\) are the correction factors, and \(a\) i , b i , c i and \(k\) i are related to the device temperature and the cut-off voltage, and empirical values can be taken. An important feature of the additional switch is that the number of inserted and removed sub-modules is the same, without changing the number of inserted sub-modules. The exchange of two sub-modules corresponds to one additional switch loss value, and its loss value includes one IGBT turn-on loss value, one IGBT turn-off loss value, and one diode reverse recovery loss value. Furthermore, the primary additional switch loss \(E\) of the converter valve can be determined add = \(E\) on (i CE ) + \(E\) off (i CE ) + \(E\) rec (i f ).

[0069] From the working state of the sub-module, it can be seen that the necessary switch action occurs at the moment when the step wave of the arm voltage jumps, corresponding to the state change of some sub-modules from inserted to removed or from removed to inserted. According to the formula the moment \(t\) of each step change can be determined n , where \(m\) represents the voltage modulation ratio, \(U\) m represents the amplitude of the valve-side phase voltage of the converter valve, and \(U\) dc represents the DC-side voltage of the converter valve. Furthermore, based on each step change moment \(t\) n , combined with the modulation wave of a single arm and the periodic waveform of the corresponding arm current, as well as the loss types corresponding to the switching process, the necessary switch loss can be determined. Specifically, the single-arm loss value when \(i\) pa is greater than 0 and the slope of \(u\) pa is greater than 0 can be determined the single-arm loss value when \(i\) pa is less than 0 and the slope of \(u\) pa is greater than 0 can be determined the single-arm loss value when \(i\) pa is less than 0 and the slope of \(u\) pa is less than 0 can be determined the single-arm loss value when \(i\) pa is greater than 0 and the slope of \(u\) pa is less than 0 can be determined where \(P\) represents the case when \(i\) pa is less than 0 and \(u\) paThe number of conducting sub - modules during the period when the slope is greater than 0, N represents the total number of conductions within a period, and q represents i pa Greater than 0 and u pa The number of sub - modules removed during the period when the slope is less than 0. Furthermore, the necessary switching loss P of the converter valve can be determined nec = 6(E nec1 + E nec2 + E nec3 + E nec4 ) / T.

[0070] Furthermore, the switching loss P of the converter valve can be determined as P = P cond + P nec .

[0071] The additional switching actions are affected by factors such as the capacitor voltage equalization strategy, operating conditions, on - site environment, and component parameters. The switching times, moments, and module selection are discrete and random, and cannot be accurately calculated through a mechanism model. Only empirical values can be taken according to the on - site situation. Therefore, only an initial valve loss value with a certain error can be calculated through the mechanism model.

[0072] Step 220: Input the actual parameters of the converter valve as input parameters into the pre - constructed mechanism model, and the output parameter is the initial value of the valve loss of the converter valve.

[0073] Among them, the actual parameters can include all the parameters mentioned in the aforementioned step 210, and all can be obtained during the actual operation of the converter valve.

[0074] Step 230: Determine a preset network model for calculating the valve loss calculation value of the converter valve, and train the preset network model to obtain a neural network.

[0075] Figure 3 This is the flowchart of step 230 in a method for calculating the loss of a converter valve provided in the second embodiment of the present invention. As Figure 3 shown, in one implementation, step 230 may specifically include:

[0076] Step 2310: Construct an initial network model based on a fully - connected network; based on the single - variable method, sequentially adjust the network structure and hyperparameters of the initial network model to obtain a preset network model.

[0077] Specifically, as a widely used neural network, the fully - connected neural network has strong data regression ability. Therefore, a fully - connected network is selected to construct the initial network model. During specific implementation, the single - variable method is used to sequentially adjust the network structure and hyperparameters of the initial network model to obtain a preset network model. The network structure may include the number of hidden layers of the network and the number of input and output nodes of each hidden layer, etc., and the hyperparameters may include the learning rate and the number of training times, etc.

[0078] Step 2320: Obtain the historical cooling water temperature, historical cooling water flow rate, historical valve hall temperature, and historical actual loss value of the converter valve within a historical time period, and obtain the initial value of the historical valve loss of the converter valve within the historical time period through the mechanism model; use the initial value of the historical valve loss, the historical cooling water temperature, the historical cooling water flow rate, the historical valve hall temperature, and the historical actual loss value as training data to perform network training on a preset network model, and calculate the loss function; perform network optimization based on the backpropagation algorithm until the loss function converges to obtain the neural network.

[0079] Specifically, the initial value of the historical valve loss, the historical cooling water temperature, the historical cooling water flow rate, and the historical valve hall temperature can be used as input information and input into the preset network model. The output information obtained is the historical test loss value. Determine the loss function based on the historical test loss value and the historical actual loss value, and determine the hyperparameters when the loss function converges. Then, determine the neural network based on the hyperparameters.

[0080] Step 240: Determine the cooling water temperature, cooling water flow rate, and valve hall temperature of the converter valve.

[0081] In one implementation, step 240 may specifically include:

[0082] Based on the inlet valve water temperature and / or outlet valve water temperature of the converter valve, determine the cooling water temperature.

[0083] Specifically, during the operation of the converter valve, the cooling water temperature, cooling water flow rate, and valve hall temperature of the converter valve can be obtained. Of course, the inlet valve water temperature and outlet valve water temperature of the cooling water passing through the converter valve can be obtained, and the inlet valve water temperature can be determined as the cooling water temperature, or the outlet valve water temperature can be determined as the cooling water temperature, or the average value of the inlet valve water temperature and the outlet valve water temperature can be determined as the cooling water temperature.

[0084] Step 250: Use the initial value of the valve loss, the cooling water temperature, cooling water flow rate, and valve hall temperature of the converter valve as input information and input into the pre-trained neural network. The output information obtained is the calculated value of the valve loss of the converter valve.

[0085] Specifically, input the obtained cooling water temperature, cooling water flow rate, valve hall temperature, and the initial value of the valve loss determined by the aforementioned mechanism model into the pre-trained neural network. The neural network can correct the initial value of the valve loss based on the cooling water temperature, cooling water flow rate, and valve hall temperature to obtain a calculated value of the valve loss that is closer to the actual value of the valve loss, making the calculation result of the valve loss more accurate.

[0086] Step 260: Determine the actual valve loss value based on the cooling water temperature and the cooling water flow rate; compare the actual valve loss value with the valve loss calculated value, and determine the accuracy of the loss calculation according to the comparison result.

[0087] Specifically, the actual valve loss value can be determined based on the temperature difference between the inlet valve water temperature and the outlet valve water temperature of the cooling water passing through the converter valve and the cooling water flow rate. Specifically, it can be based on the formula to determine the actual valve loss value, where P real represents the actual loss of the converter valve, with the unit of kw; Q represents the water flow rate, with the unit of L / h; ρ represents the water mass density, with the unit of kg / m 3 ; C represents the specific heat capacity of water, with the unit of J / (kg·K); T in represents the inlet valve water temperature, with the unit of °C, and T out represents the outlet valve water temperature, with the unit of °C.

[0088] Furthermore, the difference between the actual valve loss value and the valve loss calculated value can be compared, and the accuracy of the loss calculation can be determined according to this difference. It can be understood that the smaller the difference between the actual valve loss value and the valve loss calculated value, the higher the accuracy of the loss calculation.

[0089] Embodiment 2 of the present invention provides a method for calculating the losses of a converter valve. The method includes: determining the conduction loss and the switching loss according to the actual parameters, and constructing the mechanism model based on the conduction loss and the switching loss; inputting the actual parameters of the converter valve as input parameters into the pre-constructed mechanism model, and the output parameter is the initial value of the valve loss of the converter valve; determining a preset network model for calculating the calculated value of the valve loss of the converter valve, and training the preset network model to obtain a neural network; determining the cooling water temperature, the cooling water flow rate, and the valve hall temperature of the converter valve; inputting the initial value of the valve loss, the cooling water temperature, the cooling water flow rate, and the valve hall temperature of the converter valve as input information into the pre-trained neural network, and the output information is the calculated value of the valve loss of the converter valve; determining the actual valve loss value according to the cooling water temperature and the cooling water flow rate; comparing the actual valve loss value with the calculated value of the valve loss, and determining the accuracy of the loss calculation according to the comparison result. In the above technical solution, after constructing the mechanism model based on the conduction loss and the switching loss of the converter valve, the initial value of the valve loss is determined based on the actual parameters in the mechanism model; after training the preset network model to obtain a neural network, the calculated value of the valve loss is determined in the neural network based on the cooling water temperature, the cooling water flow rate, the valve hall temperature, and the initial value of the valve loss. On the basis of performing mechanism modeling based on the actual parameters to determine the initial value of the valve loss, a neural network is introduced to correct the calculated value of the valve loss based on the on-site measured cooling water temperature, cooling water flow rate, and valve hall temperature, so that the calculated value of the valve loss is closer to the actual valve loss value, providing a relatively accurate engineering reference value for the designers and operators of the converter valve, and after determining the actual valve loss value according to the inlet valve water temperature, outlet valve water temperature, and cooling water flow rate, comparing the actual valve loss value with the calculated value of the valve loss, and determining the accuracy of the loss calculation according to the comparison result.

[0090] Embodiment 3

[0091] Figure 4 FIG. is a schematic structural diagram of a converter valve loss calculation device provided in Embodiment 3 of the present invention. The device can be applied to situations where more accurate converter valve losses need to be calculated. The device can be implemented by software and / or hardware, and is generally integrated in a computer device.

[0092] As Figure 4 shown, the device includes:

[0093] An initial valve loss value determination module 410, configured to input the actual parameters of the converter valve as input parameters into a pre-constructed mechanism model, and the output parameter is the initial value of the valve loss of the converter valve;

[0094] The valve loss calculation value determination module 420 is configured to input the initial valve loss value, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information into a pre-trained neural network, and the output information obtained is the valve loss calculation value of the converter valve.

[0095] For the converter valve loss calculation device provided in the third embodiment, the actual parameters of the converter valve are used as input parameters and input into a pre-established mechanism model, and the output parameter obtained is the initial valve loss value of the converter valve; the initial valve loss value, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature are used as input information and input into a pre-trained neural network, and the output information obtained is the valve loss calculation value of the converter valve. In the above technical solution, first, the initial valve loss value is determined according to the actual parameters in the mechanism model, and then the valve loss calculation value is determined in the neural network according to the cooling water temperature, the cooling water flow rate, the valve hall temperature, and the initial valve loss value of the converter valve. On the basis of establishing a mechanism model based on actual parameters to determine the initial valve loss value, a neural network is introduced to correct the valve loss calculation value based on the on-site measured cooling water temperature, cooling water flow rate, and valve hall temperature, and the obtained valve loss calculation value is closer to the actual valve loss value, providing a relatively accurate engineering reference value for the designers and maintenance personnel of the converter valve.

[0096] On the basis of the above embodiment, the device further includes:

[0097] The mechanism model construction module is configured to determine the conduction loss and the switching loss according to the actual parameters, and construct the mechanism model based on the conduction loss and the switching loss.

[0098] The network model construction module is configured to construct an initial network model based on a fully connected network; based on the single variable method, sequentially adjust the network structure and hyperparameters of the initial network model to obtain a preset network model.

[0099] The network model training module is configured to obtain the historical cooling water temperature, historical cooling water flow rate, historical valve hall temperature, and historical actual loss value of the converter valve during a historical time period, and obtain the historical initial valve loss value of the converter valve during the historical time period through the mechanism model; use the historical initial valve loss value, the historical cooling water temperature, the historical cooling water flow rate, the historical valve hall temperature, and the historical actual loss value as training data to perform network training on the preset network model, and calculate the loss function; perform network optimization based on the backpropagation algorithm until the loss function converges to obtain the neural network.

[0100] The determination module is configured to determine the cooling water temperature, the cooling water flow rate, and the valve hall temperature of the converter valve.

[0101] On the basis of the above embodiments, a determination module is specifically configured to:

[0102] Determine the cooling water temperature based on the inlet valve water temperature and / or the outlet valve water temperature of the converter valve.

[0103] On the basis of the above embodiments, the device further includes:

[0104] An accuracy determination module, configured to determine an actual valve loss value according to the cooling water temperature and the cooling water flow rate; compare the actual valve loss value with a valve loss calculation value, and determine the accuracy of the loss calculation according to the comparison result.

[0105] The converter valve loss calculation device provided by the embodiments of the present invention can execute the converter valve loss calculation method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0106] It should be noted that in the embodiments of the above converter valve loss calculation device, the included units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0107] Embodiment 4

[0108] Figure 5 It is a schematic structural diagram of a computer device provided by Embodiment 4 of the present invention. Figure 5 It shows a block diagram of an exemplary computer device 5 suitable for implementing the embodiments of the present invention. Figure 5 The shown computer device 5 is only an example and should not bring any limitation to the functions and usage scope of the embodiments of the present invention.

[0109] As Figure 5 shown, the computer device 5 is presented in the form of a general-purpose computing electronic device. The components of the computer device 5 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0110] The bus 18 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the multiple bus structures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0111] The computer device 5 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 5, including volatile and non-volatile media, removable and non-removable media.

[0112] The system memory 28 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 5 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 can be used for reading and writing on non-removable, non-volatile magnetic media ( Figure 5 not shown, commonly referred to as a "hard disk drive"). Although Figure 5 not shown in the figure, a disk drive for reading and writing on removable non-volatile disks (such as "floppy disks"), and an optical disk drive for reading and writing on removable non-volatile optical disks (such as CD-ROM, DVD-ROM or other optical media) can be provided. In these cases, each drive can be connected to the bus 18 through one or more data media interfaces. The system memory 28 can include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the embodiments of the present invention.

[0113] A program / utility 40 having a set (at least one) of program modules 42 can be stored, for example, in the system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods in the embodiments described in the present invention.

[0114] The computer device 5 can also communicate with one or more external devices 14 (such as a keyboard, a pointing device, a display 24, etc.), and can also communicate with one or more devices that enable a user to interact with the computer device 5, and / or communicate with any device that enables the computer device 5 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through an input / output (I / O) interface 22. And, the computer device 5 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 20. As Figure 5 shown, the network adapter 20 communicates with other modules of the computer device 5 through the bus 18. It should be understood that although Figure 5which is not shown in the figure, other hardware and / or software modules may be used in combination with the computer device 5, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0115] The processing unit 16 executes various functional applications and page displays by running the programs stored in the system memory 28, for example, implementing the... method provided by the present embodiment. The method includes:

[0116] Taking the actual parameters of the converter valve as input parameters and inputting them into a pre-constructed mechanism model, and the obtained output parameter is the initial value of the valve loss of the converter valve;

[0117] Taking the initial value of the valve loss, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information and inputting them into a pre-trained neural network, and the obtained output information is the calculated value of the valve loss of the converter valve.

[0118] Of course, those skilled in the art can understand that the processor can also implement the technical solutions of the converter valve loss calculation method provided by any embodiment of the present invention.

[0119] Embodiment Five

[0120] Embodiment Five of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements, for example, the converter valve loss calculation method provided by the present embodiment. The method includes:

[0121] Taking the actual parameters of the converter valve as input parameters and inputting them into a pre-constructed mechanism model, and the obtained output parameter is the initial value of the valve loss of the converter valve;

[0122] Taking the initial value of the valve loss, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information and inputting them into a pre-trained neural network, and the obtained output information is the calculated value of the valve loss of the converter valve.

[0123] The computer storage medium of an embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable media may be computer-readable signal media or computer-readable storage media. The computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, the computer-readable storage media may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or component.

[0124] The computer-readable signal media may include data signals propagated in a baseband or as part of a carrier wave, which carry computer-readable program codes. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal media may also be any computer-readable media other than the computer-readable storage media, and this computer-readable media can send, propagate, or transmit a program for use by or in combination with an instruction execution system, device, or component.

[0125] The program codes contained on the computer-readable media may be transmitted by any appropriate media, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0126] The computer program codes for performing the operations of the present invention may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program codes may be executed entirely on the user's computer, partially on the user's computer, executed as an independent 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 may 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 may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0127] Those of ordinary skill in the art should understand that the various modules or steps of the present invention described above can be implemented by a general-purpose computing device. They can be centralized on a single computing device or distributed over a network composed of multiple computing devices. Optionally, they can be implemented with program codes executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0128] Note that the above is only the preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments here. Various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments only. Without departing from the concept of the present invention, it can also include more other equivalent embodiments, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for calculating the losses of a converter valve, characterized in that, it includes: Taking the actual parameters of the converter valve as input parameters and inputting them into a pre-constructed mechanism model, and the output parameter obtained is the initial value of the valve losses of the converter valve; Taking the initial value of the valve losses, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information and inputting them into a pre-trained neural network, and the output information obtained is the calculated value of the valve losses of the converter valve.

2. The method for calculating the losses of a converter valve according to claim 1, characterized in that, Before taking the actual parameters of the converter valve as input parameters and inputting them into a pre-constructed mechanism model, and the output parameter obtained is the initial value of the valve losses of the converter valve, it further includes: Determining the conduction losses and switching losses according to the actual parameters, and constructing the mechanism model based on the conduction losses and the switching losses.

3. The method for calculating the losses of a converter valve according to claim 1, characterized in that, Before taking the initial value of the valve losses, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information and inputting them into a pre-trained neural network, it further includes: Constructing an initial network model based on a fully connected network; Based on the single variable method, adjusting the network structure and hyperparameters of the initial network model in sequence to obtain a preset network model.

4. The method for calculating the losses of a converter valve according to claim 3, characterized in that, Before taking the initial value of the valve losses, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information and inputting them into a pre-trained neural network, it further includes: Obtaining the historical cooling water temperature, historical cooling water flow rate, historical valve hall temperature, and historical actual loss value of the converter valve within a historical time period, and obtaining the historical initial value of the valve losses of the converter valve within the historical time period through the mechanism model; Taking the historical initial value of the valve losses, the historical cooling water temperature, the historical cooling water flow rate, the historical valve hall temperature, and the historical actual loss value as training data to perform network training on the preset network model, and calculating the loss function; Performing network optimization based on the backpropagation algorithm until the loss function converges to obtain the neural network.

5. The method for calculating the losses of a converter valve according to claim 1, characterized in that, Before taking the initial value of the valve losses, the cooling water temperature of the converter valve, the cooling water flow rate, and the valve hall temperature as input information and inputting them into a pre-trained neural network, it further includes: Determining the cooling water temperature, cooling water flow rate, and valve hall temperature of the converter valve.

6. The method for calculating the losses of a converter valve according to claim 4, characterized in that, Determining the cooling water temperature of the converter valve includes: Based on the inlet valve water temperature and / or outlet valve water temperature of the converter valve, determining the cooling water temperature.

7. The method for calculating the losses of a converter valve according to claim 6, characterized in that, It further includes: Determining the actual valve loss value according to the cooling water temperature and the cooling water flow rate; Comparing the actual valve loss value with the calculated value of the valve losses, and determining the accuracy of the loss calculation according to the comparison result.

8. A device for calculating the losses of a converter valve, characterized in that, Including: A valve loss initial value determination module, configured to input the actual parameters of a commutation valve as input parameters into a pre-constructed mechanism model, and the obtained output parameter is the initial value of the valve loss of the commutation valve; A valve loss calculated value determination module, configured to input the initial value of the valve loss, the cooling water temperature of the commutation valve, the cooling water flow rate, and the valve hall temperature as input information into a pre-trained neural network, and the obtained output information is the calculated value of the valve loss of the commutation valve.

9. A computer device Characterized in that The device includes: At least one processor; and a memory communicatively connected to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the commutation valve loss calculation method according to any one of claims 1-7.

10. A storage medium containing computer-executable instructions, where the computer-executable instructions are used to execute the commutation valve loss calculation method according to any one of claims 1-7 when executed by a computer processor.

Images