Searching method and device for design point parameters of gas compressor and electronic equipment

Abstract

The invention provides a method and a device for searching design point parameters of a gas compressor and electronic equipment. The method comprises the steps that for a first aerodynamic design scheme of the gas compressor, candidate inlet flow of the gas compressor is determined based on a specified gas compressor flow interval and / or a trained proxy model, and the proxy model is used for predicting the inlet flow of the gas compressor; the candidate inlet flow is the associated inlet flow when the first convergence working condition occurs in the design flow searching process of the first aerodynamic design scheme; the calculated pressure ratio of the gas compressor under the first convergence working condition is obtained; on the basis of the relation between the calculated pressure ratio and the target pressure ratio, the candidate inlet flow is adjusted till the relation between the calculated pressure ratio and the target pressure ratio meets a preset condition; based on the adjusted candidate inlet flow, the target inlet flow meeting the target pressure ratio under the first aerodynamic design scheme is determined through an interpolation algorithm. The risk of compressor design point search failure can be reduced, and the number of design point search times can be reduced.

Description

Technical Field

[0001] This application relates to the technical field of compressor design, and particularly to a method, device and electronic device for searching for compressor design point parameters. Background Art

[0002] The flow-pressure ratio characteristic curve of a multi-stage compressor is relatively steep at high rotational speeds, the constant rotational speed line is almost a vertical line, and the flow margin of the compressor is very small. At this time, the design point of the compressor is usually determined by the pressure ratio. The bisection method is a conventional method for searching for the compressor design flow rate, and the design flow rate is searched within a specified flow rate search interval. However, the design flow rate may not be within the search interval, and there is a risk of failure in searching for the compressor design point.

[0003] In the aerodynamic optimization design of a compressor, the aerodynamic optimization of the compressor is usually based on a genetic algorithm. In the genetic algorithm, there is a large deviation in the sample flow rate interval between the initial population and the later population. In order to cover all samples of different generations of the population, a very wide inlet flow rate search interval needs to be set, but this will increase the number of design flow rate searches for a single sample and significantly increase the total time consumption of the compressor aerodynamic optimization. Summary of the Invention

[0004] Embodiments of this application provide a method, device and electronic device for searching for compressor design point parameters.

[0005] According to the first aspect of this application, there is provided a method for searching for compressor design point parameters, including:

[0006] For a first aerodynamic design scheme of the compressor, based on a specified compressor flow rate interval and / or a trained surrogate model for predicting the compressor inlet flow rate, determine a candidate inlet flow rate for the compressor; the candidate inlet flow rate is the inlet flow rate associated with the first convergent operating condition during the design flow rate search process of the first aerodynamic design scheme;

[0007] Obtain the calculated pressure ratio of the compressor under the first convergent operating condition;

[0008] Based on the relationship between the calculated pressure ratio and the target pressure ratio, adjust the candidate inlet flow rate until the relationship between the calculated pressure ratio and the target pressure ratio meets a preset condition;

[0009] Based on the adjusted candidate inlet flow rate, use an interpolation algorithm to determine a target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme.

[0010] According to the second aspect of this application, there is provided a device for searching for compressor design point parameters, including:

[0011] A first determination module, configured to determine a candidate inlet flow rate of the compressor for a first aerodynamic design scheme of the compressor based on a specified compressor flow rate range and / or a trained surrogate model, where the surrogate model is used to predict the compressor inlet flow rate; the candidate inlet flow rate is the inlet flow rate associated with the first convergence condition during the design flow rate search process of the first aerodynamic design scheme.

[0012] An acquisition module, configured to acquire the calculated pressure ratio of the compressor under the first convergence condition.

[0013] An adjustment module, configured to adjust the candidate inlet flow rate based on the relationship between the calculated pressure ratio and the target pressure ratio until the relationship between the calculated pressure ratio and the target pressure ratio meets a preset condition.

[0014] A second determination module, configured to determine a target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme by using an interpolation algorithm based on the adjusted candidate inlet flow rate.

[0015] According to a third aspect of the present application, there is provided an electronic device, including:

[0016] At least one processor; and

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

[0018] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the foregoing first aspect.

[0019] According to a fourth aspect of the present application, there is provided a storage medium storing instructions that, when run on an electronic device, cause the electronic device to execute the method described in the foregoing first aspect.

[0020] According to a fifth aspect of the present application, there is provided a program product including at least one of a program and instructions, and when the at least one of the program and instructions is executed by an electronic device, the steps of the method described in the foregoing first aspect are implemented.

[0021] According to the technical solution of the present application, a candidate inlet flow rate can be determined based on a specified compressor flow rate range and / or a trained surrogate model, the candidate inlet flow rate is adjusted based on the relationship between the calculated pressure ratio and the target pressure ratio, and a target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme is determined by using an interpolation algorithm based on the adjusted candidate inlet flow rate, which can reduce the risk of failure in searching for the compressor design point, thereby improving the success rate of the design point search, and can also reduce the number of design point searches, thereby reducing the total time consumption of the compressor aerodynamic optimization.

[0022] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of embodiments in conjunction with the accompanying drawings, where:

[0024] Figure 1 is a schematic flow chart of a method for searching compressor design point parameters provided by an embodiment of the present application;

[0025] Figure 2 is an example diagram of the network structure of a surrogate model provided by an embodiment of the present application;

[0026] Figure 3 is a schematic flow chart of a method for searching compressor design point parameters provided by an embodiment of the present application;

[0027] Figure 4 is an example diagram for determining the compressor flow scaling factor provided by an embodiment of the present application;

[0028] Figure 5 is an example diagram of the implementation process of a search scheme for design point parameters of a certain sample provided by an embodiment of the present application;

[0029] Figure 6 is an example diagram of the search process for the design flow of a certain sample provided by an embodiment of the present application;

[0030] Figure 7 is an example diagram of the calculation log of a certain generation population of a compressor provided by an embodiment of the present application;

[0031] Figure 8 is an example diagram of the number of design point searches for different generation populations of compressor aerodynamic optimization provided by an embodiment of the present application;

[0032] Figure 9 is a block diagram of a device for searching compressor design point parameters provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as limiting the present application.

[0034] The following describes exemplary embodiments of the present application in conjunction with the accompanying drawings. Various details of the embodiments of the present application are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0035] The terms used in one or more embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of the present application. The singular forms "a", "the", and "said" used in one or more embodiments of the present application and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to and encompasses any or all possible combinations of one or more of the associated listed items.

[0036] It should be understood that although the terms first, second, etc. may be used in one or more embodiments of the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0037] It should be noted that in the embodiments of the present application, certain industry-existing solutions such as certain software, components, models, etc. may be mentioned. They should be considered exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solution of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0038] The following describes a method, apparatus, and electronic device for searching compressor design point parameters according to embodiments of the present application with reference to the accompanying drawings.

[0039] Among them, it should be noted that the execution subject of the method for searching compressor design point parameters in the embodiments of the present application can be a device for searching compressor design point parameters. This device can be implemented in software and / or hardware, and this device can be configured in an electronic device. Exemplarily, the electronic device can include, but is not limited to, a terminal, a server, etc.

[0040] Figure 1 It is a schematic flow chart of the method for searching compressor design point parameters provided for the embodiments of the present application. As Figure 1 shown, the method for searching compressor design point parameters may include, but is not limited to, the following steps.

[0041] In step 101, for the first aerodynamic design scheme of the compressor, based on the specified compressor flow rate range and / or the trained surrogate model, determine the candidate inlet flow rate of the compressor.

[0042] In some embodiments, the first aerodynamic design scheme may be any one of multiple aerodynamic design schemes of the compressor. For example, when performing aerodynamic optimization design of the compressor based on a genetic algorithm, the first aerodynamic design scheme may be any one sample in the population. Exemplarily, the compressor may be a multi-stage compressor.

[0043] In some embodiments, the above-mentioned surrogate model can be used to predict (estimate) the compressor inlet flow rate. Exemplarily, the input of the surrogate model may include compressor geometric information, and the output of the surrogate model may include the compressor inlet flow rate. Among them, the compressor geometric information may include but is not limited to at least one of the following: internal flow path geometric information, external flow path geometric information, blade geometric information (such as blade installation angle, cut blade tip, etc.). Optionally, in some embodiments, the output of the surrogate model may further include blade efficiency, etc. Exemplarily, the above-mentioned surrogate model may be pre-trained; or, in the aerodynamic optimization design of the compressor based on a genetic algorithm, the surrogate model is trained in real time based on the sample calculation logs accumulated in the initial population, where the calculation logs detail the automatic capture process of the design points of different samples, covering the geometric information and aerodynamic performance of the optimized samples, and are the data source for training the surrogate model.

[0044] Optionally, in some embodiments, the above-mentioned surrogate model can be trained in the following way: in the aerodynamic optimization design of the compressor based on a genetic algorithm, the aerodynamic performance and geometric information of the compressor in the calculation logs can be used to train the surrogate model. Exemplarily, as Figure 2 shown, the network structure of the surrogate model can be a BP (Back Propagation) neural network. The BP neural network can include 2 hidden layers. By inputting the geometric information of the internal flow path, external flow path, and blades of the sample (where the blade geometric information can include the blade installation angle or the cut blade tip, etc.), the compressor inlet flow rate (also called the design flow rate) of the sample can be predicted. As the aerodynamic optimization of the compressor progresses, the sample calculation results accumulated in different generations of the population increase continuously. By training the surrogate model in real time, the prediction accuracy of the surrogate model can be improved.

[0045] In some embodiments, the above-mentioned candidate inlet flow rate may be the inlet flow rate associated with the first converged condition that appears during the design flow rate search process of the first aerodynamic design scheme. Exemplarily, the "converged condition" may refer to a working state where the pressure ratio can be calculated. Exemplarily, when the pressure ratio can be calculated based on the current inlet flow rate, it can be considered that a converged condition has occurred.

[0046] In an embodiment of the present application, the candidate inlet flow rate of the compressor can be determined based on a specified compressor flow rate range. In some embodiments, the candidate inlet flow rate of the compressor can be determined based on a trained surrogate model. In some embodiments, the candidate inlet flow rate of the compressor can be determined based on a specified compressor flow rate range and a trained surrogate model.

[0047] In a possible implementation, in the absence of a surrogate model, the candidate inlet flow rate of the compressor is determined based on a specified compressor flow rate range; or, in the presence of a surrogate model, flow rate prediction is performed using the surrogate model based on the compressor geometry information in the first aerodynamic design scheme. If the predicted flow rate is the inlet flow rate associated with the first converged operating condition during the design flow rate search of the first aerodynamic design scheme, the predicted flow rate is used as the candidate inlet flow rate; otherwise, the candidate inlet flow rate of the compressor is determined based on a specified compressor flow rate range.

[0048] Exemplarily, it can be detected whether there is a surrogate model. If there is no surrogate model, the candidate inlet flow rate of the compressor can be determined based on a specified compressor flow rate range. If there is a surrogate model, the candidate inlet flow rate of the compressor can be determined through the surrogate model. Exemplarily, flow rate prediction can be performed using the surrogate model based on the compressor geometry information in the first aerodynamic design scheme. If the predicted flow rate is the inlet flow rate associated with the first converged operating condition during the design flow rate search of the first aerodynamic design scheme, the predicted flow rate can be used as the candidate inlet flow rate; otherwise, the candidate inlet flow rate of the compressor can be determined based on a specified compressor flow rate range.

[0049] In some embodiments, the possible implementation of determining the candidate inlet flow rate of the compressor based on a specified compressor flow rate range can be as follows: A flow rate can be selected within the specified compressor flow rate range until the selected flow rate is the inlet flow rate associated with the first converged operating condition during the design flow rate search of the first aerodynamic design scheme, and then the selected flow rate is used as the candidate inlet flow rate of the compressor.

[0050] In a possible implementation, during the process of searching for the design flow rate of the first aerodynamic design solution, select a flow rate within the specified compressor flow rate range until the number of selections does not exceed a preset number and the selected flow rate is the inlet flow rate associated with the first converged operating condition. Then, use the selected flow rate as the candidate inlet flow rate. Exemplarily, a flow rate can be randomly selected within the specified compressor flow rate range. In the case of the selected flow rate, determine whether the pressure ratio can be calculated. If the pressure ratio can be calculated, it is determined that convergence has occurred, and the selected flow rate can be used as the candidate inlet flow rate of the compressor; otherwise, continue to randomly select a flow rate within the compressor flow rate range, and determine whether the pressure ratio can be calculated. If the pressure ratio can be calculated, it is determined that convergence has occurred, and the selected flow rate can be used as the candidate inlet flow rate of the compressor; otherwise, continue to randomly select a flow rate within the compressor flow rate range, and so on, until the number of random selections does not exceed the preset number (such as 5 times) and the selected flow rate is the inlet flow rate associated with the first converged operating condition during the search for the design flow rate of the first aerodynamic design solution. Then, use the selected flow rate as the candidate inlet flow rate of the compressor.

[0051] In some embodiments, in the case where the number of selections exceeds the preset number and the selected flow rate does not meet the inlet flow rate associated with the first converged operating condition, the compressor flow rate range can be enlarged, and the candidate inlet flow rate of the compressor can be determined based on the enlarged compressor flow rate range. Exemplarily, when the number of times of randomly selecting a flow rate within the specified compressor flow rate range exceeds the preset number (such as 5 times) and the selected flow rates do not meet the inlet flow rate associated with the first converged operating condition, the range of the compressor flow rate range can be enlarged, and a flow rate can be randomly selected within the enlarged compressor flow rate range as the candidate inlet flow rate of the compressor. Optionally, if a flow rate cannot be randomly selected within the enlarged compressor flow rate range as the candidate inlet flow rate of the compressor, continue to enlarge the compressor flow rate range until a flow rate can be randomly selected from the compressor flow rate range as the candidate inlet flow rate of the compressor.

[0052] In some embodiments, the target inlet flow rate (i.e., the target inlet flow rate that satisfies the target pressure ratio) may not be included within the specified compressor flow rate range.

[0053] In step 102, obtain the calculated pressure ratio of the compressor under the first converged operating condition.

[0054] Exemplarily, the calculated pressure ratio under the first converged operating condition may refer to the pressure ratio that can be calculated when determining the candidate inlet flow rate of the compressor within the specified compressor flow rate range and / or through a trained surrogate model.

[0055] In step 103, based on the relationship between the calculated pressure ratio and the target pressure ratio, the candidate inlet flow rate is adjusted until the relationship between the calculated pressure ratio and the target pressure ratio meets a preset condition.

[0056] In some embodiments, based on the relationship between the calculated pressure ratio and the target pressure ratio, the flow rate can be increased or decreased on the basis of the candidate inlet flow rate until the relationship between the calculated pressure ratio and the target pressure ratio meets a preset condition. Exemplarily, if the calculated pressure ratio is greater than the target pressure ratio, the flow rate can be increased on the basis of the candidate inlet flow rate; if the calculated pressure ratio is less than the target pressure ratio, the flow rate can be decreased on the basis of the candidate inlet flow rate until the relationship between the calculated pressure ratio and the target pressure ratio meets a preset condition.

[0057] In some embodiments, the relationship between the calculated pressure ratio and the target pressure ratio meeting the preset condition may include: the difference between the calculated pressure ratio and the target pressure ratio is less than or equal to a first threshold. Exemplarily, if the calculated pressure ratio is approximately equal to the target pressure ratio (or the calculated pressure ratio is near the target pressure ratio), it can be considered that the relationship between the calculated pressure ratio and the target pressure ratio meets the preset condition.

[0058] In step 104, based on the adjusted candidate inlet flow rate, an interpolation algorithm is used to determine the target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme.

[0059] In some embodiments, when the calculated pressure ratio falls near the target pressure ratio, that is, when the relationship between the calculated pressure ratio and the target pressure ratio meets the preset condition, based on the adjusted candidate inlet flow rate and the preset flow rate-pressure ratio characteristic curve, the two operating conditions closest to the target pressure ratio are selected, and an interpolation algorithm (such as a linear interpolation algorithm) is used to determine the target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme. Exemplarily, if the pressure ratio calculated under the condition of the inlet flow rate determined based on the interpolation algorithm is not equal to the target pressure ratio, the interpolation algorithm can continue to be used to determine the inlet flow rate until the pressure ratio calculated based on the determined inlet flow rate is equal to the target pressure ratio, and the inlet flow rate determined at this time is determined as the target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme.

[0060] In the above embodiments, the candidate inlet flow rate can be determined based on the specified compressor flow rate range and / or the trained surrogate model, the candidate inlet flow rate is adjusted based on the relationship between the calculated pressure ratio and the target pressure ratio, and an interpolation algorithm is used based on the adjusted candidate inlet flow rate to determine the target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme, which can reduce the risk of failure in searching for the compressor design point, thereby improving the success rate of the design point search, and can also reduce the number of design point searches, thereby reducing the total time-consuming of the compressor aerodynamic optimization.

[0061] Figure 3The flowchart shows the search method for the compressor design point parameters provided by the embodiments of the present application. As Figure 3 shown, the search method for the compressor design point parameters may include but is not limited to the following steps.

[0062] In step 301, for the first aerodynamic design scheme of the compressor, based on the specified compressor flow rate range and / or the trained surrogate model, determine the candidate inlet flow rate of the compressor.

[0063] In some embodiments, the above-mentioned candidate inlet flow rate may be the inlet flow rate associated with the first converged operating condition during the design flow rate search process of the first aerodynamic design scheme.

[0064] Optionally, step 301 may be implemented by any implementation manner in the embodiments of the present application respectively. The embodiments of the present application do not make any limitations on this and will not be elaborated further.

[0065] In step 302, obtain the calculated pressure ratio of the compressor under the first converged operating condition.

[0066] Optionally, step 302 may be implemented by any implementation manner in the embodiments of the present application respectively. The embodiments of the present application do not make any limitations on this and will not be elaborated further.

[0067] It should be noted that in some embodiments, after obtaining the calculated pressure ratio, the calculated pressure ratio may be compared with the target pressure ratio. If the calculated pressure ratio is greater than the target pressure ratio, then execute the following step 303; if the calculated pressure ratio is less than the target pressure ratio, then execute the following step 304. Optionally, in some embodiments, if the calculated pressure ratio is equal to the target pressure ratio, the inlet flow rate associated with the calculated pressure ratio may be used as the target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme. For example, if the calculated pressure ratio is the pressure ratio of the compressor under the first converged operating condition, and the inlet flow rate associated with the first converged operating condition is the candidate inlet flow rate determined based on the specified compressor flow rate range and / or the surrogate model, then the candidate inlet flow rate may be determined as the target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme.

[0068] In step 303, when the calculated pressure ratio is greater than the target pressure ratio, increase the flow rate based on the first flow rate scaling factor on the basis of the candidate inlet flow rate.

[0069] Exemplarily, when the calculated pressure ratio is greater than the target pressure ratio, the flow rate may be increased. Exemplarily, the flow rate may be increased based on the first flow rate scaling factor on the basis of the candidate inlet flow rate. In some embodiments, the first flow rate scaling factor may be preset, for example, it may be an empirical value obtained based on a large number of tests.

[0070] In step 304, when the calculated pressure ratio is less than the target pressure ratio, the flow rate is reduced based on the second flow rate scaling factor on the basis of the candidate inlet flow rate.

[0071] Exemplarily, when the calculated pressure ratio is less than the target pressure ratio, the flow rate can be reduced. Exemplarily, the flow rate can be reduced based on the second flow rate scaling factor on the basis of the candidate inlet flow rate. In some embodiments, the second flow rate scaling factor can be preset, for example, it can be an empirical value obtained based on a large number of tests. Exemplarily, the second flow rate scaling factor can be the same as or different from the first flow rate scaling factor. Exemplarily, the first flow rate scaling factor or the second flow rate scaling factor can be determined based on the flow rate-pressure ratio characteristic curve and the calculated pressure ratio.

[0072] In step 305, a new calculated pressure ratio is determined based on the adjusted candidate inlet flow rate. Based on the relationship between the new calculated pressure ratio and the target pressure ratio, the flow rate is iteratively adjusted on the basis of the adjusted candidate inlet flow rate until the relationship between the calculated pressure ratio and the target pressure ratio meets a preset condition.

[0073] Exemplarily, in the case of the adjusted candidate inlet flow rate, the new calculated pressure ratio is calculated using the pressure ratio calculation formula, and the new calculated pressure ratio is compared with the target pressure ratio. If the calculated pressure ratio is greater than the target pressure ratio, return to execute step 303, that is, increase the flow rate on the basis of the adjusted candidate inlet flow rate; if the calculated pressure ratio is less than the target pressure ratio, return to execute 304, that is, reduce the flow rate on the basis of the adjusted candidate inlet flow rate, and then determine a new calculated pressure ratio based on the adjusted candidate inlet flow rate. Based on the relationship between the new calculated pressure ratio and the target pressure ratio, the flow rate is iteratively adjusted on the basis of the adjusted candidate inlet flow rate, and so on, until the relationship between the calculated pressure ratio and the target pressure ratio meets a preset condition. Exemplarily, the relationship between the calculated pressure ratio and the target pressure ratio meeting the preset condition can include: the difference between the calculated pressure ratio and the target pressure ratio is less than or equal to the first threshold.

[0074] In some embodiments, the above-mentioned first flow scaling coefficient or second flow scaling coefficient may be determined based on a flow pressure ratio characteristic curve and a calculated pressure ratio. In one possible implementation, the first flow scaling coefficient or second flow scaling coefficient may be obtained in the following manner: Determine the first operating point parameters with the same pressure ratio as the calculated pressure ratio of the previous iteration from a pre-set flow pressure ratio characteristic curve. The first operating point parameters may include a first pressure ratio and a first inlet flow rate. The first pressure ratio is the same as the calculated pressure ratio of the previous iteration, and the first inlet flow rate is associated with the first pressure ratio. Based on the first inlet flow rate and the second inlet flow rate in the first design point parameters of the flow pressure ratio characteristic curve, determine the first flow scaling coefficient. Exemplarily, the first flow scaling coefficient or second flow scaling coefficient may be determined based on the difference between the first inlet flow rate and the second inlet flow rate in the first design point parameters of the flow pressure ratio characteristic curve. For example, taking the first flow scaling coefficient as an example, the first flow scaling coefficient may be 1 - |ε|, where ε is the difference between the above-mentioned first inlet flow rate and the second inlet flow rate, and || is the absolute value function. Wherein, in some embodiments, the flow pressure ratio characteristic curve may be used to determine the increase or decrease amplitude of the inlet flow rate.

[0075] It should be noted that the determination methods of the first flow scaling coefficient and the second flow scaling coefficient are similar. The following describes the determination of the first flow scaling coefficient as an example. For example, as Figure 4 the curve in is a certain flow pressure ratio characteristic curve, Figure 4 point A in is the design point of the flow pressure ratio characteristic curve; point B1 is the calculation result of the nth iteration of the first pneumatic design scheme (such as the second calculation convergence condition, where the first convergence condition is to determine the candidate inlet flow rate); point B2 is the operating point on the flow pressure ratio characteristic curve, and the pressure ratio of this operating point B2 is the same as the calculated pressure ratio of point B1; the inlet flow rate at point C is the same as the inlet flow rate of operating point B2, and the pressure ratio at point C is the same as the inlet flow rate at point A. Then the flow scaling coefficient of the inlet flow rate of the first pneumatic design scheme in the (n + 1)th iteration is 1 - |AC|, where AC is the difference between the inlet flow rate at point A and the inlet flow rate at point C, and the sign of this flow scaling coefficient may be determined by the calculated pressure ratio of the nth time. Exemplarily, the inlet flow rate of the first pneumatic design scheme in the (n + k)th iteration is where m(n + k) is the inlet flow rate of the (n + k)th iteration, m(n + k - 1) is the inlet flow rate of the (n + k - 1)th iteration, and sign is the sign of the flow scaling coefficient. Exemplarily, if the calculated pressure ratio of the (n + k - 1)th time is greater than the target pressure ratio (or also called the design pressure ratio), then sign = -1, otherwise sign = 1, that is, if the calculated pressure ratio of the (n + k - 1)th time is less than the target pressure ratio, then sign = 1.

[0076] In step 306, based on the adjusted candidate inlet flow rate, an interpolation algorithm is used to determine the target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme.

[0077] Optionally, step 306 can be implemented by any of the implementation manners in the embodiments of the present application. The embodiments of the present application do not limit this and will not be elaborated further.

[0078] It should be noted that those skilled in the art usually perform aerodynamic optimization design of a compressor based on algorithms. In this aerodynamic optimization process, it is necessary to evaluate the performance of the samples (i.e., aerodynamic design schemes) or the design points of each individual in the population. In order to automatically evaluate the design point performance of each individual (or sample) in the optimized population, the present application provides a search method for compressor design point parameters. To facilitate those skilled in the art to understand the present application, the following will be combined with Figure 5 to describe in detail the search scheme for the design point parameters of a certain sample in the population.

[0079] As Figure 5 shown, the implementation process of the search scheme for the design point parameters of a certain sample in the population can be as follows:

[0080] 1) Specify the compressor flow rate range, and the compressor flow rate range may not include the design flow rate (or target inlet flow rate). 2) Search for the first converged condition of the sample (such as the first aerodynamic design scheme in this article), that is: detect whether there is a surrogate model for predicting the compressor inlet flow rate. If there is a surrogate model, the compressor inlet flow rate is predicted by the surrogate model. Otherwise, randomly select the inlet flow rate within the specified compressor flow rate range. If the first converged condition does not appear, continue to randomly select the inlet flow rate within the compressor flow rate range. If the number of selections exceeds 5 times, enlarge the compressor flow rate range and continue to select the inlet flow rate within the enlarged compressor flow rate range until the first converged condition appears.

[0081] 3) In the case where the first converged condition appears, if the calculated pressure ratio is equal to the target pressure ratio, the inlet flow rate associated with the first converged condition is determined as the target inlet flow rate that meets the target pressure ratio under this sample. If the calculated pressure ratio is not equal to the target pressure ratio, the inlet flow rate can be increased or decreased according to the relationship between the calculated pressure ratio and the target pressure ratio. For example, if the calculated pressure ratio is greater than the target pressure ratio, increase the inlet flow rate. If the calculated pressure ratio is less than the target pressure ratio, decrease the inlet flow rate until the calculated pressure ratio based on the adjusted inlet flow rate is approximately equal to the target pressure ratio.

[0082] 4) When the calculated pressure ratio is near the target pressure ratio, use a linear interpolation algorithm to determine the inlet flow rate until the calculated pressure ratio is equal to the target pressure ratio, that is, the target inlet flow rate that meets the target pressure ratio under this sample can be obtained.

[0083] Figure 6 This is an example diagram of the design flow search process for a certain sample provided by an embodiment of this application. As Figure 6 shown, within the flow range (400, 600), search for the compressor inlet flow rate with a target pressure ratio of 18.5. After 11 iterations, the target inlet flow rate is obtained. The first guessed (or selected) flow rate is 560.06 kg / s, and the calculation result of the first guessed flow rate (i.e., the pressure ratio cannot be calculated, and "NaN" indicates that the pressure ratio has not been calculated) does not converge. The second guessed flow rate is 428.38 kg / s, and the calculated compressor pressure ratio (i.e., 23.94) is greater than the target pressure ratio, so the flow rate needs to be increased. The increase amplitude is determined according to Figure 4 the optional implementation shown as +20%. Starting from the 3rd iteration, the amplitude of the scaling factor is halved successively, and the sign is determined by the pressure ratio calculated in the previous time. When the calculated pressure ratio falls near the target pressure ratio, select the two operating conditions closest to the target pressure ratio, and linearly interpolate to determine the inlet flow rate for the next iteration until the calculated pressure ratio is equal to the target pressure ratio, that is, the target inlet flow rate that meets the target pressure ratio under this sample can be obtained.

[0084] Figure 7 This is an example diagram of the calculation log of a certain generation population of the compressor provided by an embodiment of this application. As Figure 7 shown, when there is no surrogate model, the compressor inlet flow rate is randomly guessed within (630, 750). At this time, 13 iterations are required to obtain the target pressure ratio, and it takes 25.2 seconds; when there is a surrogate model, the accuracy of the inlet flow rate predicted by the surrogate model is relatively high, and the target pressure ratio can be obtained after 3 iterations, taking 4.7 seconds. The calculation log details the automatic capture process of the design points of different samples, covering the geometric information and aerodynamic performance of the optimized samples, and is the data source for training the surrogate model.

[0085] Figure 8 This is an example diagram of the number of design point searches in different generation populations for the aerodynamic optimization of the compressor provided by an embodiment of this application. As Figure 8 shown, when calculating the design point of the first-generation population, since there is no surrogate model, a certain sample needs to be iterated 17 times to obtain the target pressure ratio; starting from the second-generation population, using the continuously accumulated optimized samples, the surrogate model is trained in real time, and the maximum number of iterations for each generation population gradually decreases and gradually stabilizes within 4 times. The reduction in the number of iterations of the compressor design point can significantly reduce the total time consumption of the aerodynamic optimization of the compressor. Among them, Figure 8 "iter_num" in

[0086] Figure 9The block diagram of the search device for compressor design point parameters provided by the embodiments of the present application. As Figure 9 shown, the search device for compressor design point parameters may include: a first determination module 901, an acquisition module 902, an adjustment module 903, and a second determination module 904.

[0087] Among them, the first determination module 901 is configured to, for the first aerodynamic design scheme of the compressor, determine the candidate inlet flow rate of the compressor based on the specified compressor flow rate range and / or the trained surrogate model, where the surrogate model is used to predict the compressor inlet flow rate; the candidate inlet flow rate is the inlet flow rate associated with the first converged condition during the design flow rate search process of the first aerodynamic design scheme.

[0088] The acquisition module 902 is configured to acquire the calculated pressure ratio of the compressor under the first converged condition.

[0089] The adjustment module 903 is configured to adjust the candidate inlet flow rate based on the relationship between the calculated pressure ratio and the target pressure ratio until the relationship between the calculated pressure ratio and the target pressure ratio meets the preset condition.

[0090] The second determination module 904 is configured to, based on the adjusted candidate inlet flow rate, use the interpolation algorithm to determine the target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme.

[0091] In some embodiments, the first determination module 901 is configured to: in the case where there is no surrogate model, determine the candidate inlet flow rate of the compressor based on the specified compressor flow rate range; or, in the case where there is a surrogate model, perform flow rate prediction using the surrogate model based on the compressor geometry information in the first aerodynamic design scheme. If the predicted flow rate is the inlet flow rate associated with the first converged condition during the design flow rate search process of the first aerodynamic design scheme, then use the predicted flow rate as the candidate inlet flow rate, otherwise determine the candidate inlet flow rate of the compressor based on the specified compressor flow rate range.

[0092] In some embodiments, the first determination module 901 is configured to: select a flow rate within the specified compressor flow rate range until the number of selections does not exceed the preset number and the selected flow rate is the inlet flow rate associated with the first converged condition during the design flow rate search process of the first aerodynamic design scheme, then use the selected flow rate as the candidate inlet flow rate.

[0093] In some embodiments, the first determination module 901 is further configured to: in the case where the number of selections exceeds the preset number and the selected flow rate does not meet the inlet flow rate associated with the first converged condition, enlarge the compressor flow rate range, and determine the candidate inlet flow rate of the compressor based on the enlarged compressor flow rate range.

[0094] In some embodiments, the adjustment module 903 is configured to: when the calculated pressure ratio is greater than the target pressure ratio, increase the flow rate based on a first flow rate scaling factor on the basis of the candidate inlet flow rate; or, when the calculated pressure ratio is less than the target pressure ratio, decrease the flow rate based on a second flow rate scaling factor on the basis of the candidate inlet flow rate; determine a new calculated pressure ratio based on the adjusted candidate inlet flow rate, and based on the relationship between the new calculated pressure ratio and the target pressure ratio, iteratively adjust the flow rate on the basis of the adjusted candidate inlet flow rate until the relationship between the calculated pressure ratio and the target pressure ratio meets a preset condition.

[0095] In some embodiments, the first flow rate scaling factor or the second flow rate scaling factor is obtained by the following method: determining first operating point parameters with the same pressure ratio as the calculated pressure ratio of the previous iteration from a preset flow rate-pressure ratio characteristic curve, where the first operating point parameters include a first pressure ratio and a first inlet flow rate, the first pressure ratio is the same as the calculated pressure ratio of the previous iteration, and the first inlet flow rate is associated with the first pressure ratio; and determining the first flow rate scaling factor or the second flow rate scaling factor based on the first inlet flow rate and a second inlet flow rate among the first design point parameters in the flow rate-pressure ratio characteristic curve.

[0096] In some embodiments, the surrogate model is trained by the following method: in the aerodynamic optimization design of a compressor based on a genetic algorithm, using the aerodynamic performance and geometric information in the calculation log to train the surrogate model; the input of the surrogate model includes compressor geometric information, and the output of the surrogate model includes the compressor inlet flow rate.

[0097] It should be noted that the foregoing explanation of the embodiments of the search method for compressor design point parameters also applies to the search device for compressor design point parameters in this embodiment, and will not be elaborated here.

[0098] To implement the above embodiments, the present application further provides an electronic device. The electronic device may include at least one processor and a memory. Among them, the memory is communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the search method for compressor design point parameters described in any of the foregoing embodiments.

[0099] To implement the above embodiments, the present application further provides a storage medium storing instructions that, when run on an electronic device, cause the electronic device to execute the search method for compressor design point parameters described in any of the foregoing embodiments.

[0100] To implement the above embodiments, the present application further provides a program product including at least one of a program and instructions, and when the at least one of the program and instructions is executed by an electronic device, the search method for compressor design point parameters described in any of the foregoing embodiments is implemented.

[0101] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0102] Any process or method description represented in a flowchart or described in other ways herein can be understood to represent a module, segment, or part of code including one or more executable instructions for implementing a customized logical function or process, and the scope of the preferred embodiments of this application includes additional implementations, where the functions can be executed in a manner that may not be in the order shown or discussed, including in a substantially simultaneous manner according to the involved functions or in a reverse order, which should be understood by those skilled in the art to which the embodiments of this application pertain.

[0103] The logic and / or steps represented in a flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or, if necessary, other suitable processing, and then stored in a computer memory.

[0104] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0105] Those of ordinary skill in the art can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by instructing relevant hardware through a program. The said program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0106] In addition, in each embodiment of the present application, each functional unit can be integrated in a processing module, or each unit can exist physically alone, or two or more units can be integrated in a module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0107] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for searching compressor design point parameters, characterized in that: include: For a first aerodynamic design of the compressor, determining a candidate inlet flow rate of the compressor based on a specified compressor flow interval and / or a trained surrogate model, wherein the surrogate model is used to predict the compressor inlet flow rate; The candidate inlet flow rate is the inlet flow rate associated with the first convergence condition appearing during the design flow search process of the first aerodynamic design solution; Obtaining a calculated pressure ratio of the compressor under the first convergence condition; Based on the relationship between the calculated pressure ratio and the target pressure ratio, adjusting the candidate inlet flow rate until the relationship between the calculated pressure ratio and the target pressure ratio meets a preset condition; Based on the adjusted candidate inlet flow rates, an interpolation algorithm is used to determine a target inlet flow rate that meets the target pressure ratio under the first aerodynamic design solution.

2. The method according to claim 1, characterized in that The step of determining a candidate inlet flow rate of the compressor based on a specified compressor flow rate interval and / or a trained proxy model includes: In the absence of the proxy model, determining a candidate inlet flow rate of the compressor based on the specified compressor flow rate interval; or, In the presence of the proxy model, the proxy model is used to perform flow prediction based on the compressor geometry information in the first aerodynamic design scheme. If the predicted flow is the inlet flow associated with the first convergence condition appearing during the design flow search process of the first aerodynamic design scheme, the predicted flow is used as the candidate inlet flow. Otherwise, the candidate inlet flow of the compressor is determined based on the specified compressor flow range.

3. The method according to claim 2, characterized in that The determining of the candidate inlet flow rate of the compressor based on the specified compressor flow rate interval includes: A flow rate is selected within the specified compressor flow range until the number of selections does not exceed a preset number and the selected flow rate is the inlet flow rate associated with the first convergence condition appearing during the design flow search process of the first aerodynamic design scheme, and the selected flow rate is used as the candidate inlet flow rate.

4. The method according to claim 3, characterized in that The method further comprises: When the number of selections exceeds the preset number and the selected flow does not satisfy the inlet flow associated with the occurrence of the first convergence condition, the compressor flow interval is enlarged, and the candidate inlet flow of the compressor is determined based on the enlarged compressor flow interval.

5. The method according to claim 1, characterized in that The adjusting the candidate inlet flow rate based on the relationship between the calculated pressure ratio and the target pressure ratio until the relationship between the calculated pressure ratio and the target pressure ratio satisfies a preset condition includes: When the calculated pressure ratio is greater than the target pressure ratio, the flow rate is increased based on the first flow rate scaling factor on the basis of the candidate inlet flow rate; or, when the calculated pressure ratio is less than the target pressure ratio, the flow rate is decreased based on the second flow rate scaling factor on the basis of the candidate inlet flow rate; A new calculated pressure ratio is determined based on the adjusted candidate inlet flow rate, and based on the relationship between the new calculated pressure ratio and the target pressure ratio, the flow rate is iteratively adjusted based on the adjusted candidate inlet flow rate until the relationship between the calculated pressure ratio and the target pressure ratio meets a preset condition.

6. The method according to claim 5, characterized in that The first flow scaling factor or the second flow scaling factor is obtained by: Determining a first operating point parameter having a pressure ratio that is the same as the calculated pressure ratio of the previous iteration from a preset flow-pressure ratio characteristic curve, wherein the first operating point parameter includes a first pressure ratio and a first inlet flow rate, the first pressure ratio is the same as the calculated pressure ratio of the previous iteration, and the first inlet flow rate is associated with the first pressure ratio; The first flow scaling factor or the second flow scaling factor is determined based on the first inlet flow rate and a second inlet flow rate in a first design point parameter in the flow-to-pressure ratio characteristic curve.

7. The method according to any one of claims 1 to 6, characterized in that The proxy model is trained in the following way: In the compressor aerodynamic optimization design based on genetic algorithm, the compressor aerodynamic performance and geometric information in the calculation log are used to train the proxy model; the input of the proxy model includes the compressor geometric information, and the output of the proxy model includes the compressor inlet flow rate.

8. A compressor design point parameter search device, characterized in that: include: a first determination module, configured to determine, for a first aerodynamic design scheme of the compressor, a candidate inlet flow rate of the compressor based on a specified compressor flow rate interval and / or a trained proxy model, wherein the proxy model is used to predict the compressor inlet flow rate; The candidate inlet flow rate is the inlet flow rate associated with the first convergence condition appearing during the design flow search process of the first aerodynamic design solution; An acquisition module, used for acquiring a calculated pressure ratio of the compressor under the first convergence condition; an adjustment module, configured to adjust the candidate inlet flow rate based on the relationship between the calculated pressure ratio and the target pressure ratio until the relationship between the calculated pressure ratio and the target pressure ratio satisfies a preset condition; The second determination module is used to determine a target inlet flow rate that meets the target pressure ratio under the first aerodynamic design scheme based on the adjusted candidate inlet flow rates by using an interpolation algorithm.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A storage medium storing instructions, characterized in that: When the instructions are executed on an electronic device, the electronic device is caused to execute the method according to any one of claims 1 to 7.

Images