Turbine device simulation model evolution method and apparatus, medium and computing device

Abstract

Disclosed in the present application are a turbine device simulation model evolution method and apparatus, a medium and a computing device. The turbine device simulation model evolution method comprises: acquiring current operating data of a turbine device corresponding to a condition in which inlet parameters are design parameters; on the basis of the current operating data, pre-testing a turbine device simulation model; when a pre-test result shows that the turbine device simulation model needs to evolve, preprocessing the current operating data, so as to obtain a combined data set, the combined data set comprising input data and output data corresponding to the input data; on the basis of the combined data set, building a mapping model and, by means of the mapping model, outputting an updated performance curve with the inlet parameters being the design parameters; and replacing a historical performance curve of the turbine device simulation model with the updated performance curve, so as to evolve the turbine device simulation model. Turbine device simulation models can evolve on the basis of the degree of degradation of turbine devices, so as to realistically reflect operating characteristics of the turbine devices at different life cycle stages.

Description

A turbine equipment simulation model evolution method, device, medium and computing equipment

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on January 3, 2024, with application number 2024100045449 and application name “A method, device, medium and computing device for evolving a simulation model of a turbine equipment”, the entire contents of which are incorporated by reference into the application. Technical Field

[0002] The present application relates to the field of equipment simulation technology, and in particular to a turbine equipment simulation model evolution method, device, medium and computing equipment. Background Art

[0003] Turbine equipment is a device that generates kinetic energy by causing fluid to impact its own turbine components, thereby driving the turbine components to rotate. Turbine equipment is widely used in various fields of energy and electricity, and is the core equipment of power generation systems or power systems. The operating characteristics of turbine equipment directly affect the system performance of the power generation system or power system in which it is located. Therefore, the operating characteristics of turbine equipment need to be predicted.

[0004] To facilitate the prediction of turbine operating characteristics, existing methods involve constructing a simulation model based on an actual turbine in operation. This model then simulates the turbine's operation and generates corresponding turbine operating characteristics. However, during actual operation, the turbine operating characteristics output by the simulation model deviate from the actual turbine operating characteristics.

[0005] Application Contents

[0006] The main purpose of this application is to provide a turbine equipment simulation model evolution method, device, medium and computing equipment, aiming to solve the technical problem that there is a deviation between the operating characteristics of the turbine equipment simulated output by the simulation model and the actual operating characteristics of the turbine equipment.

[0007] To achieve the above-mentioned objectives, the first aspect of the present application provides a method for evolving a turbine equipment simulation model, the method comprising: obtaining current operating data corresponding to the turbine equipment when the inlet parameters are design parameters; pre-checking the turbine equipment simulation model based on the current operating data; when the pre-check result indicates that the turbine equipment simulation model needs to evolve, pre-processing the current operating data to obtain a combined data set, wherein the combined data set includes input data and output data corresponding to the input data; constructing a mapping model based on the combined data set, and outputting an updated performance curve when the inlet parameters are design parameters through the mapping model; using the updated performance curve to replace the historical performance curve of the turbine equipment simulation model to evolve the turbine equipment simulation model.

[0008] Optionally, the current operating data at least includes flow ratio data, speed ratio data, pressure ratio data and efficiency data of the turbine equipment at the current stage; the preprocessing of the current operating data to obtain a combined data set includes: classifying the current operating data to obtain an input data set and an output data set, wherein the input data set includes the flow ratio data and the speed ratio data, and the output data set includes the pressure ratio data and the efficiency data; and correspondingly combining the data in the input data set and the data in the output data set to obtain the combined data set.

[0009] Optionally, the combined data set includes a training set and a test set; and constructing a mapping model based on the combined data set includes: performing model training on the selected machine learning model through the combined data set to obtain a mapping model, wherein the input parameters of the mapping model correspond to the data type in the input data set, and the output parameters of the mapping model correspond to the data type in the output data set.

[0010] Optionally, the mapping model is obtained by performing model training on the selected machine learning model through the combined data set, including: dividing the combined data set into a training set and a test set; performing model training on the selected machine learning model through the training set; testing the trained machine learning model through the test set, wherein the machine learning model outputs corresponding test output data based on the input data in the test set; if the test result indicates that the output accuracy of the machine learning model meets preset conditions, the machine learning model is determined as the mapping model.

[0011] Optionally, the testing of the trained machine learning model using the test set includes: determining the absolute value of the precision error between the test output data and the original output data corresponding to the input data in the test set; and comparing the absolute value of the precision error with a second preset threshold.

[0012] Optionally, the preset condition includes: the absolute value of the precision error between the test output data and the corresponding original output data is less than the second preset threshold.

[0013] Optionally, if the test result shows that the output accuracy of the machine learning model does not meet the preset conditions, the machine learning model is reselected, and the training set is used to train the reselected machine learning model, and the trained machine learning model is tested using the test set until the test result meets the preset conditions.

[0014] Optionally, the pre-inspection of the turbine equipment simulation model based on the current operating data includes: constructing a current operating curve corresponding to the turbine equipment based on the current operating data; comparing the current operating curve with a historical performance curve in the turbine equipment simulation model; comparing the difference between the historical performance curve and the current operating curve with a first preset threshold, wherein the first preset threshold is determined according to the accuracy requirement set by the user; if the difference is greater than the first preset threshold, it indicates that the turbine equipment simulation model needs to evolve; if the difference is less than or equal to the first preset threshold, it indicates that the turbine equipment simulation model does not need to evolve.

[0015] Optionally, before classifying the current operating data, the method further includes: performing data cleaning on the current operating data to remove abnormal data.

[0016] In addition, to achieve the above-mentioned purpose, an embodiment of the present application also provides a turbine equipment simulation model evolution device, which includes: a data acquisition unit, used to obtain the current operating data corresponding to the turbine equipment when the inlet parameters are design parameters; a pre-inspection unit, used to pre-inspect the turbine equipment simulation model based on the current operating data; a preprocessing unit, used to pre-process the current operating data when the pre-inspection result indicates that the turbine equipment simulation model needs to evolve, to obtain a combined data set, wherein the combined data set includes input data and output data corresponding to the input data; a model construction unit, used to construct a mapping model based on the combined data set, and output an updated performance curve when the inlet parameters are design parameters through the mapping model; an evolution unit, used to replace the historical performance curve of the turbine equipment simulation model with the updated performance curve to evolve the turbine equipment simulation model.

[0017] In addition, to achieve the above-mentioned purpose, an embodiment of the present application also provides a computer-readable storage medium, which includes instructions. When the instructions are run on a computer, the computer executes the turbine equipment simulation model evolution method described in any embodiment of the present application.

[0018] In addition, to achieve the above-mentioned purpose, an embodiment of the present application also provides a computing device, which includes: at least one processor, a memory and an input and output unit; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the turbine equipment simulation model evolution method described in any embodiment of the present application.

[0019] The turbine equipment simulation model evolution method provided in the embodiment of the present application first obtains the current operating data of the turbine equipment, which characterizes the actual operating characteristics of the turbine equipment in the current state, and then divides the current operating data into an input data set and an output data set. Thereafter, the data in the input data set and the output data set are combined to generate a combined data set, the combined data set is input into a sample library, and a machine learning model is used to perform model training based on the combined data set in the sample library to generate a mapping model, and an updated performance curve is generated by the mapping model, the updated performance curve reflects the corresponding pressure ratio and efficiency of the turbine equipment under different flow ratios and speed ratios. Finally, the historical performance curve of the turbine equipment simulation model is replaced with the updated performance curve generated by the mapping model, so that the turbine equipment simulation model can evolve according to the degree of degradation of the turbine equipment and truly reflect the operating characteristics of the turbine equipment at different life stages. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] FIG1 is a schematic flow chart of a turbine equipment simulation model evolution method provided in an embodiment of the present application;

[0021] FIG2 is a flow ratio-efficiency performance curve of a turbine equipment simulation model provided in an embodiment of the present application;

[0022] FIG3 is a flow ratio-pressure ratio performance curve of a turbine equipment simulation model provided in an embodiment of the present application;

[0023] FIG4 is a structural block diagram of a turbine equipment simulation model evolution device provided in an embodiment of the present application;

[0024] FIG5 is a schematic structural diagram of a medium provided in an embodiment of the present application;

[0025] FIG6 is a schematic diagram of the structure of a computing device provided in an embodiment of the present application.

[0026] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0027] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0028] In related technologies, turbine equipment will experience wear and degradation of components during its entire life cycle, and the performance curve output by the turbine equipment simulation model is the operating characteristics of the turbine equipment obtained by theoretical calculation. Therefore, there is a large difference between the actual operating characteristics of the degraded turbine equipment and the operating characteristics represented by the performance curve output by the turbine equipment simulation model, that is, the performance curve output by the turbine equipment simulation model is difficult to represent the actual operating characteristics of the turbine equipment.

[0029] Referring to FIG1 , to solve the above technical problems, an embodiment of the present application provides a method for evolving a turbine equipment simulation model. The method can be executed by a computing device, such as a server or a computer. The method for evolving a turbine equipment simulation model provided by the present application can include the following steps:

[0030] S10, obtaining current operating data corresponding to the turbine equipment when the inlet parameters are the design parameters.

[0031] Among them, the current operating data refers to the outlet temperature, pressure, and flow rate corresponding to the turbine equipment at different inlet temperatures, pressures, flow rates, and speeds at the current stage.

[0032] The turbine equipment inlet parameters may include inlet mass flow, inlet total pressure, inlet total temperature and inlet dynamic and static pressure difference.

[0033] It is worth noting that the current operating data obtained needs to cover the entire speed range and flow range of the turbine equipment to ensure the comprehensiveness of the operating data. Among them, the entire speed range of the turbine equipment refers to the minimum speed to the allowable overspeed range, and the flow range refers to the surge safety flow to the blockage safety flow range at each speed. Referring to Figures 2 and 3, the entire speed range of the turbine equipment shown in Figures 2 and 3 is 0.2N-1.2N. The flow ratio range multiplied by the rated flow is the flow range. For example, at a rated speed of 1.0N, the flow range of the turbine equipment is 0.39-0.97.

[0034] In this exemplary embodiment, the pressure ratio data and efficiency data of the turbine equipment at the current stage can be obtained by the following formula: rt =P t，in / P t，out η t =Δh / Δh0

[0035] Among them, P rt is the pressure ratio of the turbine equipment; P t，in is the inlet pressure of the turbine equipment, P t，out is the outlet pressure of the turbine equipment; η t is the efficiency of the turbine equipment, Δh is the actual enthalpy difference between the inlet and outlet of the turbine equipment, and Δh0 is the isentropic enthalpy difference between the inlet and outlet of the turbine equipment.

[0036] S20 , performing a pre-check on the turbine equipment simulation model based on current operating data.

[0037] Among them, the purpose of pre-checking the turbine equipment simulation model based on the current operating data is to determine whether the simulation accuracy of the turbine equipment simulation model matches the current performance of the turbine equipment, that is, to determine whether the turbine equipment simulation model needs to be evolved. It is understandable that the turbine equipment will inevitably experience performance degradation during operation, resulting in a characteristic curve offset. If the performance curve of the simulation model does not match the current performance of the turbine equipment, the simulation progress of the simulation model will decrease. This step is to pre-check the simulation model, and when the pre-check results indicate that the simulation model needs to evolve, execute subsequent steps to eliminate the characteristic curve offset and simulation accuracy reduction problems caused by equipment performance degradation.

[0038] In an exemplary embodiment, step S20 may specifically include the following process:

[0039] constructing a current operation curve of the corresponding turbine equipment based on the current operation data;

[0040] Compare current operating curves with historical performance curves from the turbine plant simulation model;

[0041] Comparing the difference between the historical performance curve and the current operating curve with a preset threshold, wherein the preset threshold is determined according to the accuracy requirement set by the user;

[0042] If the difference is greater than a preset threshold, it indicates that the turbine equipment simulation model needs to be evolved;

[0043] If the difference is less than or equal to the preset threshold, it indicates that the turbine equipment simulation model does not need to evolve.

[0044] Specifically, the turbine system features a dedicated "historical performance curve," which updates with the turbine system's current stage. Each time the turbine system simulation model evolves, the resulting turbine performance curve, assuming the inlet parameters are the design parameters, is saved as the latest "historical performance curve." Each performance curve comparison is performed against the latest historical performance curve. The first-stage "historical performance curve" is provided by the manufacturer and calibrated using the unit's initial operating data.

[0045] It can be known that the current operating data is the data obtained when the inlet parameters of the turbine equipment are the inlet design parameters. Therefore, the current operating curve constructed based on the current operating data is the operating curve when the inlet parameters are the inlet design parameters. The current operating curve can include a "flow ratio-pressure ratio curve" and a "flow ratio-efficiency curve". Therefore, this step is to compare the equipment's historical operating "flow ratio-pressure ratio curve" and "flow ratio-efficiency curve" with the current operating "flow ratio-pressure ratio curve" and "flow ratio-efficiency curve" under the premise of keeping the turbine equipment's inlet parameters as the inlet design parameters (inlet design temperature and inlet design pressure) to determine whether the deviation between the two is greater than a first preset threshold. When the deviation between the two is greater than the first preset threshold, the turbine equipment simulation model needs to evolve. Exemplarily, the current operating curve corresponding to the turbine equipment can be constructed based on the current operating data, and the current operating curve and the historical performance curve of the simulation model can be plotted in the same chart to more intuitively obtain the difference between the current operating data and the historical performance curve, so as to intuitively judge whether the turbine equipment simulation model needs to evolve. The first preset threshold can be adjusted according to the actual required accuracy. The higher the accuracy, the higher the frequency of updating the turbine equipment model. Conversely, the lower the accuracy, the lower the frequency of updating the turbine equipment model.

[0046] For example, taking a turbine as an example, its characteristic curve is shown in Figures 2 and 3. Taking the first preset threshold as 10% as an example, at the design speed of 1.0N, when the maximum deviation of the current pressure ratio and efficiency values ​​of the turbine equipment compared with the specific values ​​of the historical curve is greater than 10%, it appears that the turbine equipment simulation model needs to be evolved. The pressure ratio and efficiency values ​​are calculated under the same flow ratio and speed ratio. The maximum deviation is calculated as follows: Err1% = (Pr-Pr0) / Pr0 Err2% = (η-η0) / η0

[0047] Among them, Err1 represents the difference in pressure ratio values; Err2 represents the difference in efficiency; Pr represents the current pressure ratio; Pr0 represents the historical pressure ratio; η represents the current efficiency; η0 represents the historical efficiency, among which Pr and η are the data obtained by differencing the pressure ratio curve and efficiency curve at the design speed of 1.0N in the current operating data, and Pr0 and η0 are the data obtained by differencing the pressure ratio curve and efficiency curve at the design speed of 1.0N based on the historical performance curve.

[0048] S30 , when the pre-check result indicates that the turbine equipment simulation model needs to be evolved, pre-processing the current operating data to obtain a combined data set, wherein the combined data set includes input data and output data corresponding to the input data.

[0049] Among them, preprocessing the current operating data is to process the current operating data into input data and output data to establish a correspondence between the input data and the output data, and then obtain an updated performance curve corresponding to the current operating data through the mapping model constructed in subsequent steps. The updated performance curve is used to replace the historical performance curve in the turbine equipment simulation model.

[0050] In this exemplary embodiment, the current operating data may include flow ratio data, speed ratio data, pressure ratio data and efficiency data of the turbine equipment at the current stage, wherein the flow ratio data represents the ratio of the fluid output flow rate to the fluid input flow rate of the turbine equipment at the current stage, the speed ratio data represents the ratio of the operating speed to the rated speed of the turbine equipment at the current stage, the pressure ratio data represents the ratio of the fluid pressure at the inlet to the flow pressure at the outlet of the turbine equipment at the current stage, and the efficiency data represents the working speed of the turbine equipment performing operations at the current stage.

[0051] On this basis, step S30 may specifically include the following process:

[0052] Classifying current operating data to obtain an input data set and an output data set, wherein the input data set includes flow ratio data and speed ratio data, and the output data set includes pressure ratio data and efficiency data;

[0053] The data in the input dataset and the data in the output dataset are correspondingly combined to obtain a combined dataset.

[0054] Specifically, the current operating data includes the operating data of the corresponding turbine equipment obtained under different operating conditions of the turbine equipment. In order to facilitate the subsequent fitting of the operating status of the current turbine equipment, the current operating data can be classified and divided into an input data set and an output data set. The input data set is used as the input parameter of the mapping model in subsequent steps, and the output data set is used as the output parameter of the mapping model in subsequent steps. Dividing the current operating data into an input data set and an output data set can not only facilitate the subsequent fitting of the data of the turbine equipment at the current stage, but also improve the efficiency of data processing.

[0055] Combining the data in the input dataset with the data in the output dataset establishes a mapping relationship between the data in the input dataset and the data in the output dataset, thereby obtaining a combined dataset. In other words, the combined dataset indicates the output data corresponding to the turbine equipment under the current input data, that is, the combined dataset reflects the actual operating conditions of the turbine equipment at the current stage. By obtaining the input dataset and the corresponding output dataset, the mapping relationship of the turbine equipment under the current operating conditions can be obtained, thereby facilitating the accurate determination of the current operating status of the turbine equipment.

[0056] In an exemplary embodiment, a data processing model can be established to process the current operating data of the turbine equipment into an input dataset and a combination of input datasets to generate a combined dataset. The combined dataset constitutes a sample library for the machine learning model in subsequent steps. Based on this combined dataset, the data processing model can automatically filter pressure ratio data and efficiency data under different flow ratios and speed ratios at the design inlet pressure and design inlet temperature, forming a sample library for machine learning.

[0057] In an exemplary embodiment, before classifying the current operating data, the method may further include the following step: performing data cleaning on the current operating data to remove abnormal data.

[0058] Specifically, the turbine's current operating data can be obtained from measurements of sensor elements installed within the turbine. Sensor elements can wear out during use, leading to errors. Data cleaning primarily removes abnormal data caused by sensor aging or failure. Preprocessing the current operating data ensures its comprehensiveness and validity, generating preprocessed operating data that can be used for subsequent classification and sample library generation.

[0059] S40, constructing a mapping model based on the combined data set, and outputting an updated performance curve when the import parameters are the design parameters through the mapping model.

[0060] As described above, the combined dataset is obtained by classifying the current operating data and reflects the corresponding relationship between input data and output data. This step is to construct a mapping model using the above combined dataset, and the mapping model outputs an updated performance curve that is compatible with the current operating data. It can be understood that the updated performance curve of the turbine equipment is obtained by changing the flow rate and speed while maintaining the design inlet pressure and inlet temperature constant. The updated performance curve can be a curve of the flow ratio data-pressure ratio data of the turbine equipment at different speeds, or a curve of the flow ratio data-efficiency data of the turbine equipment at different speeds.

[0061] In an exemplary embodiment, the mapping model may be constructed by specifically including the following process:

[0062] The mapping model is obtained by training the selected machine learning model with the combined data set, wherein the input parameters of the mapping model correspond to the data types in the input data set, and the output parameters of the mapping model correspond to the data types in the output data set.

[0063] Specifically, the machine learning model may include, for example, a decision tree model, a KN algorithm model, a random forest model, or a logistic regression model, and preferably a decision tree model or a neural network model. After the machine learning model is selected, the combined data set may be used to train the machine learning model to obtain a mapping model.

[0064] Furthermore, the combined dataset can be further divided into a training set and a test set. The training set is used for model training to obtain a mapping model, and the test set is used to test the constructed mapping model to detect whether the constructed mapping model meets the requirements. On this basis, the model training of the selected machine learning model using the combined dataset to obtain the mapping model can specifically include the following process:

[0065] Perform model training on the selected machine learning model using the training set;

[0066] Testing the trained machine learning model using a test set, where the machine learning model outputs corresponding test output data based on the input data in the test set;

[0067] If the test results show that the output accuracy of the machine learning model meets the preset conditions, the machine learning model is determined as a mapping model.

[0068] Testing the trained machine learning model on the test set is to test the accuracy of the trained model. This process can specifically include determining the absolute value of the accuracy error between the test output data and the original output data corresponding to the input data in the test set, and comparing the absolute value of the accuracy error with a second preset threshold. The input data and output data in the test set have a one-to-one correspondence, and the original output data is the output data in the test set, i.e., the original output data set is the actual output data of the turbine equipment. The test output data is the data output by the trained model based on the input data in the test set. This step involves inputting the input data in the test set into the trained model, and then outputting the corresponding data from the trained model as the test output data. The test output data is then compared with the original output data corresponding to the input data in the test set, and the deviation between the original output data and the test output data is used to test whether the trained model meets the accuracy requirements. If the accuracy requirements are met, the trained model is determined as the final mapping model. Otherwise, if the accuracy requirements are not met, the subsequent steps are performed to retrain the model until a mapping model that meets the accuracy requirements is obtained.

[0069] In this exemplary embodiment, the preset condition may be that the absolute value of the accuracy error between the test output data and the corresponding original output data is less than a second preset threshold. Obviously, if the accuracy error between the test output data and the original output data is less than the second preset threshold, it indicates that the trained model meets the accuracy requirements, and the trained model can be determined as the final mapping model. On the contrary, if the absolute value of the accuracy error between the test output data and the corresponding original output data is greater than or equal to the second preset threshold, it indicates that the currently trained model does not meet the accuracy requirements. At this time, the machine learning model can be reselected, and the training set can be used to train the reselected machine learning model, and the test set can be used to test the trained machine learning model until the test results meet the preset conditions. In addition, it should be understood that when the output accuracy of the machine learning model does not meet the preset conditions, the parameter range and sample library can be expanded to perform the above-mentioned model training and testing process until the required accuracy is achieved.

[0070] In this step, a mapping model is obtained through sample learning. Based on the mapping model, the pressure ratio and efficiency of the turbine equipment under any flow ratio and speed ratio can be obtained. That is, the mapping model can output an updated performance curve that matches the current operating characteristics of the turbine equipment with the inlet parameters being the design parameters.

[0071] S50, replacing the historical performance curve of the turbine equipment simulation model with the updated performance curve to evolve the turbine equipment simulation model.

[0072] Among them, this step is to replace the historical performance curve of the turbine equipment simulation model, because the updated performance curve is obtained based on the current operating conditions of the turbine equipment. Therefore, by using the updated performance curve to replace the historical performance curve of the simulation model,

[0073] By replacing the existing historical performance curve of the turbine equipment simulation model with an updated performance curve corresponding to the current operating conditions of the turbine equipment at the current stage, the evolution of the historical performance curve of the turbine equipment simulation model is completed. In this way, the historical performance curve of the turbine equipment simulation model at the current stage can accurately simulate the operating characteristics of the turbine equipment at the current stage, and accurately reflect the performance of the turbine equipment after performance degradation, so that the turbine equipment simulation model has the function of evolving according to the degree of performance degradation.

[0074] The embodiment of the present application first obtains the current operating data of the turbine equipment, which characterizes the actual operating characteristics of the turbine equipment in its current state. The current operating data is then divided into an input data set and an output data set. The data in the input data set and the output data set are then combined to generate a combined data set. The combined data set is input into a sample library, and a machine learning model is used to train the model based on the combined data set in the sample library to generate a mapping model. The mapping model generates an updated performance curve, which reflects the pressure ratio and efficiency of the turbine equipment under different flow ratios and speed ratios. Finally, the historical performance curve of the turbine equipment simulation model is replaced with the updated performance curve generated by the mapping model, so that the turbine equipment simulation model can evolve according to the degree of degradation of the turbine equipment and truly reflect the operating characteristics of the turbine equipment at different life stages. The turbine equipment simulation model evolution method provided in the embodiment of the present application can solve the problem of reduced simulation accuracy of the turbine equipment simulation model due to equipment performance degradation throughout its life cycle, ensure that the operating characteristics of the turbine equipment can be simulated with high precision at different stages of its life cycle, and accurately simulate the behavioral characteristics of the turbine equipment at different performance degradation levels at different stages of its full cycle operation. It is an effective method for building a digital twin of the turbine equipment.

[0075] Referring to FIG4 , based on the above embodiment, the present application further provides a turbine equipment simulation model evolution device. The turbine equipment simulation model evolution device 400 provided in the present application may include a data acquisition unit 410 , a pre-check unit 420 , a pre-processing unit 430 , a model construction unit 440 and an evolution unit 450 , wherein:

[0076] The data acquisition unit 410 may be used to acquire current operating data corresponding to the turbine equipment when the inlet parameters are the design parameters;

[0077] The pre-check unit 420 may be used to pre-check the turbine equipment simulation model based on current operating data;

[0078] The preprocessing unit 430 can be used to preprocess the current operating data to obtain a combined data set when the pre-check result indicates that the turbine equipment simulation model needs to be evolved, wherein the combined data set includes input data and output data corresponding to the input data;

[0079] The model building unit 440 may be configured to build a mapping model based on the combined data set, and output an updated performance curve under which the import parameters are the design parameters through the mapping model;

[0080] The evolution unit 450 may be configured to replace the historical performance curve of the turbine equipment simulation model with the updated performance curve to evolve the turbine equipment simulation model.

[0081] In an exemplary embodiment, the preprocessing unit 430 can also be specifically used to: classify the current operating data to obtain an input data set and an output data set, wherein the input data set includes flow ratio data and speed ratio data, and the output data set includes pressure ratio data and efficiency data; and correspondingly combine the data in the input data set and the data in the output data set to obtain a combined data set.

[0082] In an exemplary embodiment, the combined data set may include a training set and a test set, and the model building unit 440 may also be specifically used to: perform model training on the selected machine learning model using the combined data set to obtain a mapping model, wherein the input parameters of the mapping model correspond to the data type in the input data set, and the output parameters of the mapping model correspond to the data type in the output data set.

[0083] In an exemplary embodiment, the model building unit 440 can also be specifically used to: divide the combined data set into a training set and a test set; perform model training on the selected machine learning model through the training set; test the trained machine learning model through the test set, wherein the machine learning model outputs corresponding test output data based on the input data in the test set; if the test result shows that the output accuracy of the machine learning model meets the preset conditions, the machine learning model is determined as a mapping model.

[0084] In an exemplary embodiment, the model building unit 440 can also be specifically used to: test the trained machine learning model through a test set, including: determining the absolute value of the accuracy error between the test output data and the original output data corresponding to the input data in the test set; comparing the absolute value of the accuracy error with a second preset threshold.

[0085] In an exemplary embodiment, the preset condition may include: an absolute value of a precision error between the test output data and the corresponding original output data is smaller than a second preset threshold.

[0086] In an exemplary embodiment, the model building unit 440 can also be specifically used to: if the test results show that the output accuracy of the machine learning model does not meet the preset conditions, then reselect the machine learning model, and use the training set to train the reselected machine learning model, and use the test set to test the trained machine learning model until the test results meet the preset conditions.

[0087] In an exemplary embodiment, the pre-check unit 420 can also be specifically used to: construct a current operating curve corresponding to the turbine equipment based on current operating data; compare the current operating curve with the historical performance curve of the turbine equipment, wherein the historical performance curve is output by the turbine equipment simulation model; compare the difference between the historical performance curve and the current operating curve with a first preset threshold, wherein the first preset threshold is determined according to the accuracy requirements set by the user; if the difference is greater than the first preset threshold, it indicates that the turbine equipment simulation model needs to evolve; if the difference is less than or equal to the first preset threshold, it indicates that the turbine equipment simulation model does not need to evolve.

[0088] In an exemplary embodiment, the turbine equipment simulation model evolution device 400 may further include a data cleaning unit, which may be used to clean current operating data to remove abnormal data.

[0089] It should be understood that the turbine equipment simulation model evolution device 400 provided in this exemplary embodiment can execute the turbine equipment simulation model evolution method described in any of the above embodiments, and accordingly has the beneficial effects described in any of the above embodiments, which will not be repeated here.

[0090] On the basis of the above embodiments, the embodiments of the present application also provide a computer-readable storage medium. Referring to Figure 5, the computer-readable storage medium shown therein is a CD 50 on which a computer program (i.e., a program product) is stored. When the computer program is executed by the processor, it will implement the various steps described in the above method implementation, for example, obtaining the current operating data corresponding to the turbine equipment when the inlet parameters are the design parameters; pre-checking the turbine equipment simulation model based on the current operating data; when the pre-check results indicate that the turbine equipment simulation model needs to evolve, pre-processing the current operating data to obtain a combined data set, wherein the combined data set includes input data and output data corresponding to the input data; constructing a mapping model based on the combined data set, and outputting an updated performance curve when the inlet parameters are the design parameters through the mapping model; using the updated performance curve to replace the historical performance curve of the turbine equipment simulation model to evolve the turbine equipment simulation model; the specific implementation methods of each step will not be repeated here.

[0091] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0092] In addition, based on the above embodiments, the present application also provides a computing device. FIG6 shows a block diagram of an exemplary computing device 60 suitable for implementing the embodiments of the present application. The computing device 60 can be a computer system or a server. The computing device 60 shown in FIG6 is merely an example and should not limit the functionality or scope of use of the embodiments of the present application.

[0093] As shown in FIG6 , the components of computing device 60 may include, but are not limited to, one or more processors or processing units 601 , a system memory 602 , and a bus 603 connecting different system components (including system memory 602 and processing unit 601 ).

[0094] The computing device 60 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 60, including volatile and non-volatile media, removable and non-removable media.

[0095] The system memory 602 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 6021 and / or cache memory 6022. The computing device 60 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, ROM 6023 may be used to read and write non-removable, non-volatile magnetic media (not shown in FIG. 6 , commonly referred to as a “hard drive”). Although not shown in FIG. 6 , a disk drive for reading and writing a removable non-volatile disk (such as a “floppy disk”) and an optical disk drive for reading and writing a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to a bus 603 connecting different system components via one or more data medium interfaces. The system memory 602 may include at least one program product having a set (such as at least one) of program modules that are configured to perform the functions of each embodiment of the present application.

[0096] A program / utility 6025 having a set (at least one) of program modules 6024 may be stored, for example, in system memory 602. Such program modules 6024 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 6024 generally implement the functions and / or methods of the embodiments described herein.

[0097] The computing device 60 may also communicate with one or more external devices 604 (e.g., a keyboard, pointing device, display, etc.). Such communication may be performed via an input / output (I / O) interface 605. Furthermore, the computing device 60 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 606. As shown in FIG6 , the network adapter 606 communicates with other modules of the computing device 60 (e.g., processing unit 601, etc.) via a bus 603 that connects various system components. It should be understood that, although not shown in FIG6 , other hardware and / or software modules may be used in conjunction with the computing device 60.

[0098] The processing unit 601 executes various functional applications and data processing by running programs stored in the system memory 602. For example, it obtains current operating data corresponding to the turbine equipment when the inlet parameters are the design parameters; performs a pre-check on the turbine equipment simulation model based on the current operating data; when the pre-check results indicate that the turbine equipment simulation model needs to be evolved, pre-processes the current operating data to obtain a combined data set, wherein the combined data set includes input data and output data corresponding to the input data; constructs a mapping model based on the combined data set, and outputs an updated performance curve when the inlet parameters are the design parameters through the mapping model; and replaces the historical performance curve of the turbine equipment simulation model with the updated performance curve to evolve the turbine equipment simulation model. The specific implementation methods of each step are not repeated here. It should be noted that although the above detailed description mentions several units / modules or sub-units / sub-modules of the robot motion trajectory processing device, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided to be embodied by multiple units / modules.

[0099] In the description of this application, it should be noted that the terms "first", "second" and "third" are used for descriptive purposes only and should not be understood as indicating or implying relative importance.

[0100] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. There may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some communication interface, indirect coupling or communication connection of devices or units, which may be electrical, mechanical or other forms.

[0102] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0103] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0104] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0105] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The scope of protection of the present application is not limited thereto. Although the present application has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present application, or perform equivalent replacements for some of the technical features thereof. These modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the scope of protection of the claims.

[0106] Furthermore, although the operations of the method of the present application are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in this particular order, or that all illustrated operations must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

Claims

1. A method for evolving a simulation model of a turbine device, wherein, The method includes: Obtaining the current operation data corresponding to the turbine equipment when the inlet parameters are design parameters; Pre-checking the turbine equipment simulation model based on the current operation data; When the pre-check result indicates that the turbine equipment simulation model needs to be evolved, preprocessing the current operation data to obtain a combined data set, where the combined data set includes input data and output data corresponding to the input data; Constructing a mapping model based on the combined data set and outputting an updated performance curve with the inlet parameters being design parameters through the mapping model; Using the updated performance curve to replace the historical performance curve of the turbine equipment simulation model to evolve the turbine equipment simulation model.

2. The method for evolving a simulation model of a turbine device according to claim 1, wherein, The current operation data at least includes flow ratio data, speed ratio data, pressure ratio data, and efficiency data of the turbine equipment at the current stage; The preprocessing the current operation data to obtain a combined data set includes: Classifying the current operation data to obtain an input data set and an output data set, where the input data set includes the flow ratio data and the speed ratio data, and the output data set includes the pressure ratio data and the efficiency data; Correspondingly combining the data in the input data set and the data in the output data set to obtain the combined data set.

3. The turbine equipment simulation model evolution method according to claim 2, wherein, The combined data set includes a training set and a test set; the constructing a mapping model based on the combined data set includes: Training a selected machine learning model through the combined data set to obtain a mapping model, where the input parameters of the mapping model correspond to the data types in the input data set, and the output parameters of the mapping model correspond to the data types in the output data set.

4. The method for evolving a simulation model of a turbine device according to claim 3, wherein, The training a selected machine learning model through the combined data set to obtain a mapping model includes: Dividing the combined data set into a training set and a test set; Training a selected machine learning model through the training set; Testing the trained machine learning model through the test set, where the machine learning model outputs corresponding test output data based on the input data in the test set; If the test result indicates that the output accuracy of the machine learning model meets the preset conditions, determining the machine learning model as the mapping model.

5. The turbine equipment simulation model evolution method according to claim 4, wherein, The testing the trained machine learning model through the test set includes: Determining the absolute value of the accuracy error between the test output data and the original output data corresponding to the input data in the test set; Comparing the absolute value of the accuracy error with a second preset threshold.

6. The turbine equipment simulation model evolution method according to claim 5, wherein, The preset conditions include: The absolute value of the accuracy error between the test output data and the corresponding original output data is less than the second preset threshold.

7. The turbine equipment simulation model evolution method according to claim 5, wherein, If the test result indicates that the output accuracy of the machine learning model does not meet the preset conditions, reselecting a machine learning model, training the reselected machine learning model using the training set, and testing the trained machine learning model using the test set until the test result meets the preset conditions.

8. The method for evolving a simulation model of a turbine device according to claim 1, wherein, Pre-inspecting the turbine equipment simulation model based on the current operation data includes: Constructing a current operation curve corresponding to the turbine equipment based on the current operation data; Comparing the current operation curve with the historical performance curve in the turbine equipment simulation model; Comparing the difference between the historical performance curve and the current operation curve with a first preset threshold, where the first preset threshold is determined according to the accuracy requirement set by the user; If the difference is greater than the first preset threshold, it indicates that the turbine equipment simulation model needs to be evolved; If the difference is less than or equal to the first preset threshold, it indicates that the turbine equipment simulation model does not need to be evolved.

9. The method for evolving a simulation model of a turbine device according to claim 2, wherein, Before classifying the current operation data, the method further includes: Performing data cleaning on the current operation data to remove abnormal data.

10. A turbine equipment simulation model evolution device, wherein, The device includes: A data acquisition unit for acquiring the current operation data corresponding to the turbine equipment when the inlet parameters are design parameters; A pre-inspection unit for pre-inspecting the turbine equipment simulation model based on the current operation data; A preprocessing unit for preprocessing the current operation data to obtain a combined data set when the pre-inspection result indicates that the turbine equipment simulation model needs to be evolved, where the combined data set includes input data and output data corresponding to the input data; A model construction unit for constructing a mapping model based on the combined data set and outputting an updated performance curve with inlet parameters being design parameters through the mapping model; An evolution unit for replacing the historical performance curve of the turbine equipment simulation model with the updated performance curve to evolve the turbine equipment simulation model.

11. A computer-readable storage medium, wherein, It includes instructions that, when running on a computer, cause the computer to execute the turbine equipment simulation model evolution method according to any one of claims 1 to 9.

12. A computing device, wherein, The computing device includes: At least one processor, a memory, and an input / output unit; Wherein, the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the turbine equipment simulation model evolution method according to any one of claims 1 to 9.

Images