A turbine blade heat exchange coefficient data completion method based on multi-source data fusion

Abstract

The present application relates to the field of high-precision measurement technology, and discloses a turbine blade heat transfer coefficient data completion method based on multi-source data fusion, comprising: acquiring non-occluded area surface distribution data, occluded area discrete point data and full-area CFD simulation data, and mapping to the same parameter coordinate system; calculating the deviation of the measured value and the CFD value of the discrete points in the occluded area, and generating a continuous deviation field accordingly, correcting the CFD data in the occluded area with the deviation field, and determining the completion data of the non-measured points in the occluded area in combination with the distance weight; and fusing the completion data, the discrete point data and the non-occluded area surface distribution data to obtain full-area heat transfer coefficient data. The present application integrates multi-source data, calibrates the local error of CFD with measured points, realizes physical-guided correction through the deviation field, makes the completion data consistent with the measured accuracy and continue the CFD physical trend, solves the problems of data mutation and physical inconsistency in the traditional method, and significantly improves the accuracy and rationality of the data in the occluded area.

Description

Technical Field

[0001] This invention relates to the field of high-precision measurement technology, specifically to a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion. Background Technology

[0002] Accurate measurement of the heat transfer coefficient of turbine blades is a core aspect of cooling design for aero-engines and gas turbines, directly impacting blade lifespan and engine reliability. Currently, the main technical solutions for obtaining the surface distribution of heat transfer coefficients on blades fall into the following categories: transient liquid crystal technology and steady-state heat flow method (using temperature-sensitive paint). In turbine blade heat transfer coefficient measurement experiments, due to complex geometric structures such as the leading edge, grooved blade tip, and blade root edge, the flow and heat transfer conditions are extremely complex. Non-contact imaging measurements using transient liquid crystal (or temperature-sensitive paint) cannot obtain complete surface distribution heat transfer coefficient data in areas with poor optical visibility (obstruction).

[0003] While existing technologies can use the copper block method to measure the heat transfer coefficient and obtain discrete point measurements of the shielded area, or introduce computational fluid dynamics (CFD) data to complete the surface distribution of the heat transfer coefficient in the shielded area, these technologies suffer from the following core problems: CFD simulations introduce systematic errors due to model simplification and boundary condition approximation, resulting in local inconsistencies with measured values ​​from the copper block method; directly using uncorrected CFD data or performing simple interpolation can easily cause data abrupt changes at the boundary between the completed and measurable areas, leading to poor physical continuity and rationality, affecting the reliability of the completion results, and consequently limiting the accuracy of cooling blade design. Furthermore, inaccurate heat transfer coefficient predictions may pose a potential risk of blade ablation. No single method can achieve high-precision, full-coverage measurements across all surface areas, and simply combining CFD simulations with experimental data can cause data abrupt changes and physical discontinuities at the boundary between the completed and measurable areas due to systematic errors. Summary of the Invention

[0004] This invention provides a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion, in order to solve the problems of large errors and data mutations when simply combining CFD simulation and experimental data.

[0005] In a first aspect, the present invention provides a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion, the method comprising: Acquire surface distribution data of the unobstructed area of ​​the turbine blade, discrete point data of the obstructed area, and CFD simulation data of the entire area, and map the surface distribution data, discrete point data, and CFD simulation data to the same parametric coordinate system; Calculate the deviation between the mapped discrete point data and the corresponding CFD simulation data, and calculate the continuous deviation field of the occluded area based on the deviation. The CFD simulation data of discrete points in the shading area is corrected using a continuous deviation field, and the supplementary data is determined based on the corrected CFD simulation data of the discrete points. The supplementary data is used to characterize the heat transfer coefficient at locations other than the discrete points in the shading area. The heat transfer coefficient data of the entire turbine blade area is obtained by fusing the completed data, discrete point data, and surface distribution data of the unobstructed area after mapping.

[0006] The present invention provides a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion. This method effectively integrates high-resolution surface distribution data, real measurement data of local discrete points, and full-field information from CFD simulation. It uses real measurement data to calibrate the local systematic errors of CFD in the obstructed area, constructs a continuous deviation field for physical guidance correction, and achieves a smooth transition and optimal combination of the corrected CFD data and the original CFD physical trend in the completed area. Finally, it is seamlessly integrated with the surface distribution data of the measurable area, which significantly improves the accuracy and physical rationality of the completed data in the obstructed area. It overcomes the problems of data mutation and physical inconsistency caused by traditional methods that rely solely on CFD completion or simple interpolation, and provides a more reliable data foundation for the refined cooling design of turbine blades.

[0007] In one optional implementation, acquiring surface distribution data of the unobstructed area of ​​the turbine blade, discrete point data of the obstructed area, and CFD simulation data of the entire area includes: The heat transfer coefficient of the unshielded area of ​​the turbine blade was obtained as surface distribution data by using liquid crystal measurement of temperature-sensitive paint. The heat transfer coefficients of multiple preset discrete points in the shaded area are obtained using the copper block method as discrete point data. Computational fluid dynamics numerical simulation software was used to perform CFD simulations to obtain the heat transfer coefficient of the entire turbine blade region as CFD simulation data.

[0008] In one optional implementation, mapping the surface distribution data, discrete point data, and CFD simulation data to the same parametric coordinate system includes: A two-dimensional coordinate system is established along the blade height and arc length directions of the turbine blade. Based on the two-dimensional coordinate system, the three-dimensional coordinates of each point on the turbine blade are parameterized to obtain the standardized coordinates of each point. The two-dimensional coordinate system is divided into a structured mesh to obtain a parametric coordinate system. Based on the parametric coordinate system, the parametric coordinates of each point on the turbine blade are determined, and the surface distribution data, discrete point data, and CFD simulation data corresponding to the parametric coordinates of each point are recorded.

[0009] The present invention provides a method for completing the heat transfer coefficient data of turbine blades based on multi-source data fusion. It obtains the original measurement data and CFD simulation data of the unobstructed area and the obstructed area through traditional methods, ensuring the reliability of the original data. By mapping the three-dimensional complex surface of the turbine blade to a two-dimensional parameter plane, multi-source data fusion is performed based on the two-dimensional parameter plane, simplifying the processing difficulty, avoiding fusion errors caused by coordinate misalignment, and improving the efficiency and accuracy of subsequent multi-source data fusion.

[0010] In one optional implementation, the deviation between the mapped discrete point data and the corresponding CFD simulation data is calculated, and a continuous deviation field of the occluded region is calculated based on the deviation, including: For each discrete point within the occluded area, calculate the deviation between the discrete point data and the corresponding CFD simulation data; Based on the parameter coordinates and corresponding deviations of each discrete point, the continuous deviation field of the heat transfer coefficient in the shielded region is calculated using radial basis function interpolation.

[0011] In one alternative implementation, determining the complete data based on the corrected discrete-point CFD simulation data includes: Calculate the Euclidean distance between locations outside the discrete points in the occluded area and each discrete point, and determine the minimum Euclidean distance; The attenuation coefficient for locations outside the discrete points of the occluded region is determined by cross-validation, and the corrected weights for locations outside the discrete points of the occluded region are determined by a weighting function based on the minimum Euclidean distance and the attenuation coefficient. The heat transfer coefficients at locations outside the discrete points in the shading region are calculated based on the corrected weights, CFD simulation data of discrete points, and CFD simulation data of corrected discrete points as supplementary data.

[0012] The present invention provides a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion. It uses the measured data of discrete points in the obstructed area as "anchor points" to calibrate the local systematic error of the CFD numerical simulation data in this area. It constructs a continuous local deviation field through radial basis function interpolation and uses this deviation field to correct the CFD data in the obstructed area, rather than simply scaling the global data, so that it is closer to the physical reality. The correction weight is determined by Euclidean distance and cross-validation, so that the completed data of non-measurement point positions in the obstructed area not only matches the measured value of discrete points, but also attenuates reasonably with distance. This allows the completed data of the obstructed area to have both measured accuracy and regional consistency.

[0013] In one optional implementation, the completed data, discrete point data, and surface distribution data of the mapped unobstructed area are fused to obtain the heat transfer coefficient data of the entire turbine blade region, including: By using fluid dynamic physical constraints as a penalty term, and employing compactly supported radial basis functions to fuse and interpolate the completed data, discrete point data, and surface distribution data of the mapped unobstructed region, the continuous distribution heat transfer coefficient in the parametric coordinate system is obtained. By using surface reconstruction, the two-dimensional coordinates of the turbine blade in the parametric coordinate system are reconstructed into three-dimensional coordinates, and the continuously distributed heat transfer coefficients in the parametric coordinate system are mapped to the three-dimensional coordinate system to obtain the heat transfer coefficient data of the entire turbine blade region.

[0014] The present invention provides a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion. Through an adaptive weighted fusion algorithm, the corrected high-precision CFD data (covering the obscured area) is seamlessly and smoothly connected with the high-resolution surface distribution data (non-obscured area) obtained by transient liquid crystal measurement, thereby generating a physically consistent and continuous heat transfer coefficient distribution across the entire field. During the fusion process, fluid dynamics physical constraints are embedded to make the completion result more in line with physical laws, and the two-dimensional spatial data is reconstructed back into three-dimensional space to generate a three-dimensional heat transfer coefficient distribution, which is convenient for engineering analysis and design.

[0015] In one alternative implementation, the method further includes: In the unobstructed area, a preset number of data points are randomly obstructed, and the data completion values ​​of the preset number of points are completed using any of the data completion methods in the first aspect based on the remaining data in the area distribution data. Obtain the actual measurement values ​​of a preset number of points, and calculate the completion error based on the completion values ​​of the preset number of points and the actual measurement values, so as to verify the accuracy of the data completion method in any of the first aspects; The first measurement error of the unobstructed area, the second measurement error of the obstructed area, and the model uncertainty of the CFD simulation are obtained, and the uncertainty of the completed data is calculated based on the first measurement error, the second measurement error, and the model uncertainty.

[0016] The present invention provides a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion. By verifying the accuracy of the completion method through random shading in non-shading areas, the method directly verifies the accuracy of the completion method by utilizing the error between the completed value and the true value. This avoids the blindness of relying solely on theoretical derivation. By integrating multi-source errors, the uncertainty of the completed data is quantified, and the credible range of the results is clarified. This achieves a dual reliability guarantee for the data completion method, making the completed data both accurate and controllable.

[0017] Secondly, the present invention provides a turbine blade heat transfer coefficient data completion device based on multi-source data fusion, the device comprising: The data mapping module is used to acquire surface distribution data of the unobstructed area of ​​the turbine blade, discrete point data of the obstructed area, and CFD simulation data of the entire area, and to map the surface distribution data, discrete point data, and CFD simulation data to the same parametric coordinate system. The deviation calculation module is used to calculate the deviation between the mapped discrete point data and the corresponding CFD simulation data, and calculate the continuous deviation field of the occluded area based on the deviation. The data completion module is used to correct the CFD simulation data of discrete points in the shading area using a continuous deviation field, and to determine the completion data based on the corrected CFD simulation data of the discrete points. The completion data is used to characterize the heat transfer coefficient at locations other than the discrete points in the shading area. The multi-source data fusion module is used to fuse the completed data, discrete point data, and surface distribution data of the unobstructed area after mapping to obtain the heat transfer coefficient data of the entire turbine blade area.

[0018] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method described in the first aspect or any corresponding embodiment thereof.

[0019] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of a turbine blade heat transfer coefficient data completion method based on multi-source data fusion according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the data acquisition structure in the turbine blade heat transfer coefficient data completion method based on multi-source data fusion according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the second process of the turbine blade heat transfer coefficient data completion method based on multi-source data fusion according to an embodiment of the present invention. Figure 5 A complete flowchart of a specific embodiment of the turbine blade heat transfer coefficient data completion method based on multi-source data fusion according to an embodiment of the present invention; Figure 6This is a structural block diagram of a turbine blade heat transfer coefficient data completion device based on multi-source data fusion according to an embodiment of the present invention. Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0024] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0025] As an optional application scenario of this invention, such as Figure 1 As shown, the data completion system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0026] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0027] This invention provides a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion. By using discrete point measured data to calibrate and correct local system deviations in CFD-obscured areas, and fusing multi-source data, the method aims to reduce errors and data mutations during multi-source data fusion and improve the accuracy of the completed data.

[0028] According to an embodiment of the present invention, a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0029] This embodiment provides a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion, which can be used in the aforementioned computer system. Figure 2 This is a flowchart of a turbine blade heat transfer coefficient data completion method based on multi-source data fusion according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps: Step S201: Obtain the surface distribution data of the unobstructed area of ​​the turbine blade, the discrete point data of the obstructed area, and the CFD simulation data of the entire area, and map the surface distribution data, discrete point data, and CFD simulation data to the same parameter coordinate system.

[0030] Specifically, such as Figure 3 The diagram shows a schematic of a structure for measuring the heat transfer coefficient of a turbine blade. The unobstructed areas of the turbine blade include the blade head and back sides, while the obstructed areas include the leading edge and root edge. The heat transfer coefficient of the unobstructed area can be acquired using a camera; the heat transfer coefficient of discrete points in the obstructed area can be measured using the copper block method; and CFD simulations are performed using relevant CFD software to obtain CFD simulation data for the entire turbine blade area. To achieve the fusion of heterogeneous data, it is necessary to statistically analyze the surface distribution data, discrete point data, and CFD simulation data at the same location on the turbine blade and map them to the same parametric coordinate system. For example, for a discrete point B, its position in the parametric coordinate system is B', and its discrete point data is B''. cu Its CFD simulation data is B CFD This allows us to determine the discrete point data and corresponding CFD simulation data for the same discrete point B.

[0031] Step S202: Calculate the deviation between the mapped discrete point data and the corresponding CFD simulation data, and calculate the continuous deviation field of the occluded area based on the deviation.

[0032] Specifically, the deviation between the mapped discrete point data and the corresponding CFD simulation data is calculated, and interpolation is performed based on the deviation of each discrete point in the occluded area to determine the continuous deviation field of the occluded area.

[0033] Step S203: The CFD simulation data of discrete points in the shading area is corrected using a continuous deviation field, and the supplementary data is determined based on the corrected CFD simulation data of discrete points. The supplementary data is used to characterize the heat transfer coefficient at locations other than the discrete points in the shading area.

[0034] Specifically, since the CFD simulation data is the full-area CFD simulation data of the turbine blade, including the CFD simulation data of the shading area, but the CFD simulation data is inaccurate, the continuous deviation field of the shading area is used to correct the CFD simulation data to obtain corrected CFD simulation data.

[0035] The heat transfer coefficient at discrete points is the accurate value obtained from actual measurements. The heat transfer coefficient at discrete points in the shaded area is determined by correcting the CFD simulation data and the original CFD simulation data. The reliability of the corrected CFD simulation data varies depending on the distance from the discrete points. Therefore, the complete data for the shaded area can be determined based on the distance from each point to the discrete points, using the corrected CFD simulation data for the discrete points and the original CFD simulation data.

[0036] Step S204: The completed data, discrete point data, and surface distribution data of the mapped non-shaded area are fused to obtain the heat transfer coefficient data of the entire turbine blade area.

[0037] Specifically, the heat transfer coefficient of the shielded area can be determined by combining the heat transfer coefficients of locations other than the discrete points in the shielded area with the discrete point data. The surface distribution data of the unshielded area is the surface distribution heat transfer coefficient. By fusing the heat transfer coefficients of the shielded area and the surface distribution heat transfer coefficients of the unshielded area, the data at the boundary between the shielded and unshielded areas is smoothly transitioned, and the heat transfer coefficient data of the entire turbine blade area is obtained. This heat transfer coefficient data can be statistically analyzed using point coordinates in a two-dimensional parametric coordinate system or using point coordinates in a three-dimensional spatial coordinate system.

[0038] The turbine blade heat transfer coefficient data completion method based on multi-source data fusion provided in this embodiment effectively integrates high-resolution surface distribution data, real measurement data of local discrete points, and full-field information from CFD simulation. It uses real measurement data to calibrate the local systematic errors of CFD in the obstructed area, constructs a continuous deviation field for physical guidance correction, and achieves a smooth transition and optimal combination of the corrected CFD data and the original CFD physical trend in the completion area. Finally, it is seamlessly integrated with the surface distribution data of the measurable area, which significantly improves the accuracy and physical rationality of the completion data in the obstructed area. It overcomes the problems of data mutation and physical inconsistency caused by traditional reliance on CFD completion or simple interpolation, and provides a more reliable data foundation for the refined cooling design of turbine blades.

[0039] This embodiment provides a method for completing turbine blade heat transfer coefficient data based on multi-source data fusion, which can be used in the aforementioned computer system. Figure 4 This is a flowchart of a turbine blade heat transfer coefficient data completion method based on multi-source data fusion according to an embodiment of the present invention, as shown below. Figure 4 As shown, the process includes the following steps: Step S301: Obtain the surface distribution data of the unobstructed area of ​​the turbine blade, the discrete point data of the obstructed area, and the CFD simulation data of the entire area, and map the surface distribution data, discrete point data, and CFD simulation data to the same parameter coordinate system.

[0040] Specifically, step S301 includes: Step S3011: The heat transfer coefficient of the unshielded area of ​​the turbine blade is obtained as surface distribution data using the liquid crystal measurement temperature-sensitive paint measurement method.

[0041] Specifically, thermosensitive paint is a type of coating that changes color with temperature. When applied to the unshaded areas of turbine blades (such as the front of the blade or the unshaded area of ​​the blade body), the temperature varies at different locations when the turbine blades are working, and the thermosensitive paint will display different colors. These color changes are then captured by an LCD camera, and combined with a preset color-temperature correspondence, the temperature of each point on the blade surface can be calculated. This allows the continuous heat transfer coefficient of the unshaded area to be derived as surface distribution data.

[0042] Step S3012: Use the copper block method to obtain the heat transfer coefficients of multiple preset discrete points in the shading area as discrete point data.

[0043] Specifically, a copper block is a high-precision temperature measurement carrier. A small copper block is attached to the area blocked by the blade (such as the root or leading edge of the blade). When the blade is working, the copper block will heat up synchronously with the blade. By measuring the temperature change of the copper block, the heat transfer coefficient at that point can be calculated. By attaching copper blocks to discrete points at multiple key locations in the blocked area, the heat transfer coefficients at these points can be obtained as discrete point data.

[0044] Step S3013: Use computational fluid dynamics numerical simulation software to perform CFD simulation and obtain the heat transfer coefficient of the entire turbine blade region as CFD simulation data.

[0045] Specifically, computational fluid dynamics is a simulation experiment. It uses specialized software to create a three-dimensional model of the turbine blades, and then inputs the engine's airflow velocity, temperature and other operating parameters. The software will simulate the heat exchange process between the airflow and the blade surface, and calculate the heat transfer coefficient of the entire region as CFD simulation data.

[0046] In step S3014, a two-dimensional coordinate system is established along the blade height and arc length directions of the turbine blade, and the three-dimensional coordinates of each point on the turbine blade are parameterized based on the two-dimensional coordinate system to obtain the standardized coordinates of each point.

[0047] Specifically, turbine blades are complex three-dimensional curved surfaces, and it is difficult to directly process the position coordinates of each point and multi-source data. Therefore, a two-dimensional arc length-blade height coordinate system is used for parameter mapping.

[0048] Unfold the three-dimensional surface of the blade along the spanwise (i.e., the blade height direction) and chordwise (i.e., the arc length direction). For any point P(x,y,z) on the blade surface, its corresponding parametric coordinates (u,v) are calculated by integrating the arc length and normalizing with the blade height:

[0049] Where s is the arc length from the leading edge of the blade to the current point P, L is the total arc length, h is the blade height at the current point P, H is the total blade height, and (u,v) represents the standardized coordinates in the two-dimensional coordinate system. After mapping, the values ​​of u and v are both in the range of [0,1].

[0050] Step S3015: Perform structured meshing on the two-dimensional coordinate system to obtain the parametric coordinate system, and determine the parametric coordinates of each point on the turbine blade based on the parametric coordinate system. Record the surface distribution data, discrete point data and CFD simulation data corresponding to the parametric coordinates of each point.

[0051] Specifically, within the parameter domain (u,v), the occlusion region By performing structured mesh generation, a parametric coordinate system is obtained. Each mesh node in the parametric coordinate system is denoted as: ,in, Indicates the first One grid node, Indicates the first The coordinates of each grid node in the parametric coordinate system are recorded. The positions of discrete points in the occluded area within the parametric coordinate system are also recorded. and the corresponding measured values ​​of heat transfer coefficients and CFD simulation values Simultaneously, the positions of each point in the unobstructed area in the parametric coordinate system and their corresponding heat transfer coefficients are recorded to form surface distribution data in the parametric coordinate system.

[0052] The turbine blade heat transfer coefficient data completion method based on multi-source data fusion provided in this embodiment obtains the original measurement data and CFD simulation data of the unobstructed area and the obstructed area through traditional methods, ensuring the reliability of the original data. By mapping the three-dimensional complex surface of the turbine blade to the two-dimensional parameter plane, multi-source data fusion is performed based on the two-dimensional parameter plane, simplifying the processing difficulty, avoiding fusion errors caused by coordinate misalignment, and improving the efficiency and accuracy of subsequent multi-source data fusion.

[0053] Step S302: Calculate the deviation between the mapped discrete point data and the corresponding CFD simulation data, and calculate the continuous deviation field of the occluded area based on the deviation.

[0054] Specifically, step S302 includes: Step S3021: For each discrete point within the occluded area, calculate the deviation between the discrete point data and the corresponding CFD simulation data.

[0055] Specifically, at each discrete point location within the shaded area, the deviation between the discrete point data (i.e., the measured data of the heat transfer coefficient at discrete point locations measured using the copper block method) and the corresponding CFD simulation data is calculated to calibrate the systematic bias of the CFD data. It should be noted that the deviation can be relative or absolute. The choice between relative and absolute deviation depends on the distribution characteristics of the error. If the heat transfer coefficient varies significantly (exceeding a preset threshold for magnitude variation), relative deviation is used to eliminate the influence of dimensions. The formula for calculating the relative deviation is:

[0056] in, Indicates relative deviation. Indicates position and the corresponding measured values ​​of heat transfer coefficients, Indicates position The CFD simulation values ​​of the heat transfer coefficient and its corresponding value.

[0057] The formula for calculating absolute deviation is:

[0058] in, Indicates absolute deviation. Indicates position and the corresponding measured values ​​of heat transfer coefficients, Indicates position The CFD simulation values ​​of the heat transfer coefficient and its corresponding value.

[0059] Step S3022: Based on the parameter coordinates and corresponding deviations of each discrete point, the continuous deviation field of the heat transfer coefficient of the shielded area is calculated using radial basis function interpolation.

[0060] Specifically, based on the parameter coordinates of each discrete point and the corresponding deviation value Radial basis function interpolation is used to cover the entire occlusion area. continuous deviation field Radial basis functions (RBFs) are suitable for interpolating scattered data and are easily extended to high-dimensional spaces. A continuous bias field representation can be constructed using an RBF interpolation model as follows:

[0061] in, Radial basis functions, commonly used are quadratic functions. or Gaussian function , This represents the shape parameter, used to control the smoothness of the function; This is a low-order polynomial used to ensure the compatibility of interpolation; it is usually a linear polynomial. ; The weights and polynomial coefficients are determined by solving the following system of linear equations:

[0062] By constructing a continuous deviation field through interpolation, the nonlinear error distribution caused by local flow structures (such as eddies and reattachment) can be effectively captured, which is more accurate than the global correction model.

[0063] Step S303: The CFD simulation data of discrete points in the shading area is corrected using a continuous deviation field, and the supplementary data is determined based on the corrected CFD simulation data of discrete points. The supplementary data is used to characterize the heat transfer coefficient at locations other than the discrete points in the shading area.

[0064] Specifically, using the constructed continuous deviation field Raw CFD simulation data of discrete points in the occluded region Make corrections based on relative deviation. The constructed continuous deviation field is Its correction formula is:

[0065] Based on absolute deviation The constructed continuous deviation field is Its correction formula is:

[0066] Corrected CFD data The positions of discrete points in the shading area are strictly consistent with the measured values ​​of the copper block method, while the positions outside the discrete points are determined by the smooth transition of the deviation field.

[0067] Specifically, step S303 includes: Step S3031: Calculate the Euclidean distance between the location outside the discrete points in the occluded area and each discrete point, and determine the minimum Euclidean distance.

[0068] Specifically, an adaptive weighting strategy is adopted, making the completion results more dependent on the corrected CFD data near the measurement points, while appropriately preserving the physical trends of the original CFD data far from the measurement points. The calculation is performed at locations outside the discrete points of the occluded area. With each discrete point European distance And determine the minimum Euclidean distance: .

[0069] Step S3032: Determine the attenuation coefficient of the location outside the discrete point of the occluded area through cross-validation, and determine the corrected weight of the location outside the discrete point of the occluded area using a weight function based on the minimum Euclidean distance and the attenuation coefficient.

[0070] Specifically, a distance-dependent weight function is defined. :

[0071] in, Current location Euclidean distance to the nearest discrete point; It is the attenuation coefficient, which controls the rate at which the weight decays with distance. Its value is related to the density of measurement points and is usually determined through cross-validation. The specific determination method is a mature existing technology and will not be elaborated here.

[0072] Step S3033: Calculate the heat transfer coefficient at locations outside the discrete points in the shading area based on the corrected weights, the CFD simulation data of the discrete points, and the CFD simulation data of the corrected discrete points, as supplementary data.

[0073] Specifically, based on the corrected weights CFD simulation data of discrete points CFD simulation data of the corrected discrete points The heat transfer coefficient at locations outside the discrete points in the shaded area is calculated to complete the data for the shaded region. The formula is as follows:

[0074] By employing an adaptive weighting strategy, we ensure that sparse regions of data do not overly rely on potentially inaccurate local corrections, thus maintaining the physical rationality of the understanding.

[0075] The turbine blade heat transfer coefficient data completion method based on multi-source data fusion provided in this embodiment uses the measured data of discrete points in the obstructed area as "anchor points" to calibrate the local systematic error of the CFD numerical simulation data in this area. A continuous local deviation field is constructed by radial basis function interpolation. This deviation field is used to correct the CFD data in the obstructed area, rather than simply scaling the global data, so that it is closer to the physical reality. The correction weight is determined by Euclidean distance and cross-validation, so that the completed data at non-measurement point locations in the obstructed area not only matches the measured values ​​of discrete points, but also attenuates reasonably with distance. This allows the completed data in the obstructed area to have both measured accuracy and regional consistency.

[0076] Step S304: The completed data, discrete point data, and surface distribution data of the mapped non-shaded area are fused to obtain the heat transfer coefficient data of the entire turbine blade area.

[0077] Specifically, step S304 includes: Step S3041: Using the fluid dynamics physical constraints as a penalty term, the Compactly Supported Radial Basis Function (CSRBF) is used to fuse and interpolate the completed data, discrete point data, and surface distribution data of the mapped unshaded area to obtain the continuous distribution heat transfer coefficient in the parametric coordinate system.

[0078] Specifically, to ensure a smooth transition at the boundary between unobstructed and obstructed regions, a tightly supported radial basis function is used to complete the data. The discrete point data and the surface distribution data of the mapped unobstructed area are fused and interpolated to obtain the heat transfer coefficient distribution of the entire region. This is determined by solving the following variational problem:

[0079] in, This is a data fitting term that ensures the fusion result is achieved at liquid crystal measurement points in the unobstructed area. The value is close to the measured value; It is a regularization term and a thin-plate spline smoothing term, used to control the smoothness of the solution. It is a regularization parameter; It refers to the entire parametric blade surface.

[0080] The solution to this problem can also be expressed in the form of radial basis functions:

[0081] in, Represents the set of center points The points in the grid include all liquid crystal or thermosensitive paint data points and grid points for completing the obscured areas; It is a CSRBF that satisfies the positive definite condition, for example Its support radius is set according to the data density.

[0082] During the fusion process, fluid dynamics physical constraints are embedded to make the completed results more consistent with physical laws. For example, the heat transfer coefficient is typically low in the vortex core region at the tip of the fluted blade, while it increases in the flow reattachment region. Constraint introduction method: Physical constraints can be added to the variational problem as penalty terms. For example, if the CFD results predict the location... If a high heat transfer gradient exists (such as a reattachment line), a penalty term can be added. ,in These are constraint weights.

[0083] Step S3042: The two-dimensional coordinates of the turbine blade in the parametric coordinate system are reconstructed into three-dimensional coordinates using surface reconstruction, and the continuously distributed heat transfer coefficients in the parametric coordinate system are mapped to the three-dimensional coordinate system to obtain the heat transfer coefficient data of the entire turbine blade region.

[0084] Specifically, the continuously distributed heat transfer coefficient obtained in the parametric coordinate system By mapping the non-uniform rational B-spline (NURBS) surface reconstruction technique back to the three-dimensional solid surface of the turbine blade, a three-dimensional heat transfer coefficient distribution in physical space is generated, which facilitates engineering analysis and design. The NURBS surface reconstruction technique is a mature existing technology and will not be elaborated here.

[0085] The turbine blade heat transfer coefficient data completion method based on multi-source data fusion provided in this embodiment uses an adaptive weighted fusion algorithm to seamlessly and smoothly connect the corrected high-precision CFD data (covered and obscured areas) with the high-resolution surface distribution data (unobscured areas) obtained by transient liquid crystal measurement, thereby generating a physically consistent and continuous heat transfer coefficient distribution across the entire field. During the fusion process, fluid dynamics physical constraints are embedded to make the completion results more in line with physical laws, reconstructing the two-dimensional spatial data back into three-dimensional space to generate a three-dimensional heat transfer coefficient distribution, which is convenient for engineering analysis and design.

[0086] In some alternative implementations, the method further includes: Step S205: Randomly occlude a preset number of data points within the non-occluded area, and based on the remaining data in the surface distribution data, use the data completion method in any embodiment to complete the completion values ​​of the preset number of points.

[0087] Specifically, to evaluate the accuracy of the heat transfer coefficient data completion method provided in this embodiment, a method of artificial masking and completion comparison is adopted in the non-masked area measurable by the liquid crystal. Inside, a preset number of data points are randomly blocked. The remaining data in the surface distribution data is used as known data. The heat transfer coefficient of the blocked preset number of points is completed using the data completion method in any embodiment, and the completed value is used as the completion value.

[0088] Step S206: Obtain the actual measurement values ​​of a preset number of points, and calculate the completion error based on the completion values ​​of the preset number of points and the actual measurement values ​​to verify the accuracy of the data completion method in any embodiment.

[0089] Specifically, the actual measurement values ​​of a preset number of points are obtained using the liquid crystal measurement method for temperature-sensitive paint. The completion error is calculated based on the completion values ​​of the preset number of points and the actual measurement values ​​to verify the accuracy of the data completion method in any embodiment. The formulas for calculating the root mean square error (RMSE) and mean absolute percentage error (MAPE) are as follows:

[0090]

[0091] in, This indicates the number of preset number of points that are obscured.

[0092] Step S207: Obtain the first measurement error of the unobstructed area, the second measurement error of the obstructed area, and the model uncertainty of the CFD simulation, and calculate the uncertainty of the completed data based on the first measurement error, the second measurement error, and the model uncertainty.

[0093] Specifically, based on the error propagation theory, the uncertainty of the quantification result is analyzed, and the main sources of uncertainty include liquid crystal measurement errors. Measurement error of copper block method and CFD model uncertainty , padding value Total uncertainty It can be approximated as:

[0094] The turbine blade heat transfer coefficient data completion method based on multi-source data fusion provided in this embodiment verifies the accuracy of the completion method by randomly shading the non-shading area and directly verifying the accuracy of the completion method by using the error between the completed value and the true value. This avoids the blindness of relying solely on theoretical derivation. By integrating multi-source errors, the uncertainty of the completed data is quantified, and the credible range of the results is clarified. This achieves a dual reliability guarantee for the data completion method, making the completed data both accurate and controllable.

[0095] In one specific implementation, such as Figure 5The diagram shown is a complete flowchart of this embodiment, specifically including: Step a1: Collect three types of data from multiple sources: (1) Use the liquid crystal thermosensitive paint method to obtain the surface distribution data of the heat transfer coefficient in the unshaded area of ​​the blade (resolution 0.5mm×0.5mm); (2) Use the copper block method to select 6 discrete points in the shaded areas of the blade root and leading edge, and measure the discrete point data of their heat transfer coefficients; (3) Use CFD software (such as Fluent) to simulate and obtain the simulated data of the heat transfer coefficient of the entire blade area.

[0096] Step a2: Data preprocessing and coordinate unification. Establish a two-dimensional parametric coordinate system along the blade height and arc length directions. Convert the three-dimensional coordinates of the three types of data into standardized coordinates under this two-dimensional coordinate system and divide the data into a 200×150 structured grid to complete the data spatial alignment.

[0097] Step a3, Deviation Field and Supplementary Branch (Left Branch): Calculate the deviation between the measured values ​​and CFD simulation values ​​of the discrete points of the six occlusion areas to obtain the local discrete deviation values; based on radial basis function interpolation, extend the discrete deviation into a continuous deviation field covering the entire occlusion area.

[0098] Step a4, Data Features and Supplementary Branch (Right Branch): Use the continuous deviation field of discrete points in the occluded area to correct the CFD simulation data and obtain the preliminary corrected CFD data; calculate the Euclidean distance between the non-measurement points and discrete points in the occluded area, determine the attenuation coefficient through cross-validation, and use a weighted function (the closer the distance, the higher the weight) to generate the occluded area supplementary data.

[0099] Step a5: Multi-source data fusion integrates the surface distribution data of the unobstructed area, the data to be completed in the obstructed area, and the discrete point data in a two-dimensional grid. A gradient smoothing algorithm is used for the boundary area to ensure that the data is continuous and without abrupt changes.

[0100] Step a6: Generate and output the fused full-area heat transfer coefficient distribution of the blade (covering all areas such as the blade body, blade root, and leading edge).

[0101] Step a7, verification and uncertainty quantification: 10 points are randomly occluded in the unoccluded area. The points are then filled in using this method and compared with the true values ​​to obtain the filling error (root mean square error ≤ 4%). Integrating the error sources of the thermosensitive paint (error ± 2%), the copper block method (error ± 3%), and CFD simulation (model uncertainty ± 5%), the total uncertainty of the filled data is calculated to be ± 6.5%.

[0102] Step a8: Complete the output results. The final output is a cloud map and data file showing the heat transfer coefficient distribution of the entire turbine blade area, which will be used for subsequent cooling structure design.

[0103] This embodiment also provides a turbine blade heat transfer coefficient data completion device based on multi-source data fusion. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0104] This embodiment provides a turbine blade heat transfer coefficient data completion device based on multi-source data fusion, such as... Figure 6 As shown, it includes: The data mapping module 601 is used to acquire the surface distribution data of the unobstructed area of ​​the turbine blade, the discrete point data of the obstructed area, and the CFD simulation data of the entire area, and to map the surface distribution data, discrete point data, and CFD simulation data to the same parametric coordinate system.

[0105] The deviation calculation module 602 is used to calculate the deviation between the mapped discrete point data and the corresponding CFD simulation data, and to calculate the continuous deviation field of the occluded area based on the deviation.

[0106] The data completion module 603 is used to correct the CFD simulation data of discrete points in the shading area using a continuous deviation field, and to determine the completion data based on the corrected CFD simulation data of the discrete points. The completion data is used to characterize the heat transfer coefficient at locations other than the discrete points in the shading area.

[0107] The multi-source data fusion module 604 is used to fuse the completed data, discrete point data and the surface distribution data of the unobstructed area after mapping to obtain the heat transfer coefficient data of the entire turbine blade area.

[0108] In some alternative implementations, the data mapping module 601 includes: The first data acquisition unit is used to obtain the heat transfer coefficient of the unshielded area of ​​the turbine blade as surface distribution data using the liquid crystal measurement temperature-sensitive paint measurement method.

[0109] The second data acquisition unit is used to obtain the heat transfer coefficients of multiple preset discrete points in the shading area as discrete point data using the copper block method.

[0110] The third data acquisition unit is used to perform CFD simulations using computational fluid dynamics numerical simulation software to obtain the heat transfer coefficient of the entire turbine blade region as CFD simulation data.

[0111] The parameterization processing unit is used to establish a two-dimensional coordinate system along the blade height and arc length directions of the turbine blade, and to parameterize the three-dimensional coordinates of each point on the turbine blade based on the two-dimensional coordinate system to obtain the standardized coordinates of each point.

[0112] Mesh generation units are used to perform structured mesh generation on a two-dimensional coordinate system to obtain a parametric coordinate system. Based on the parametric coordinate system, the parametric coordinates of each point on the turbine blade are determined, and the surface distribution data, discrete point data, and CFD simulation data corresponding to the parametric coordinates of each point are recorded.

[0113] In some alternative implementations, the deviation calculation module 602 includes: The discrete point deviation calculation unit is used to calculate the deviation between the discrete point data and the corresponding CFD simulation data for each discrete point within the occluded area.

[0114] The deviation field construction unit is used to calculate the continuous deviation field of the heat transfer coefficient of the shielded area by radial basis function interpolation based on the parameter coordinates and corresponding deviations of each discrete point.

[0115] In some alternative implementations, the data completion module 603 includes: The distance calculation unit is used to calculate the Euclidean distance between the location outside the discrete points in the occluded area and each discrete point, and to determine the minimum Euclidean distance.

[0116] The corrected weight calculation unit is used to determine the attenuation coefficient of the location outside the discrete point of the occluded area through cross-validation, and to determine the corrected weight of the location outside the discrete point of the occluded area using a weight function based on the minimum Euclidean distance and the attenuation coefficient.

[0117] The data completion calculation unit is used to calculate the heat transfer coefficient of the location outside the discrete points of the shading area as completion data based on the corrected weights, the CFD simulation data of the discrete points, and the CFD simulation data of the corrected discrete points.

[0118] In some alternative implementations, the multi-source data fusion module 604 includes: The multi-source data fusion interpolation unit is used to treat fluid dynamics physical constraints as penalty terms and use compactly supported radial basis functions to fuse and interpolate the completed data, discrete point data, and surface distribution data of the mapped unobstructed region to obtain the continuously distributed heat transfer coefficient in the parametric coordinate system.

[0119] The three-dimensional surface reconstruction unit is used to reconstruct the two-dimensional coordinates of the turbine blade in the parametric coordinate system into three-dimensional coordinates using surface reconstruction, and to map the continuously distributed heat transfer coefficients in the parametric coordinate system to the three-dimensional coordinate system to obtain the heat transfer coefficient data of the entire turbine blade area.

[0120] The turbine blade heat transfer coefficient data completion device based on multi-source data fusion provided in this embodiment of the invention can execute the turbine blade heat transfer coefficient data completion method based on multi-source data fusion provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0121] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0122] The following is a detailed reference. Figure 7 This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 701, which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 702 or a program loaded from memory 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0123] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 7 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0124] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 709, or installed from a memory 708, or installed from a ROM 702. When the computer program is executed by the processor 701, it performs the functions defined in the turbine blade heat transfer coefficient data completion method based on multi-source data fusion according to embodiments of the present invention.

[0125] Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0126] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the turbine blade heat transfer coefficient data completion method based on multi-source data fusion shown in the above embodiments is implemented.

[0127] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for completing turbine blade heat transfer coefficient data based on multi-source data fusion, characterized in that, The method includes: Acquire surface distribution data of the unobstructed area of ​​the turbine blade, discrete point data of the obstructed area, and CFD simulation data of the entire area, and map the surface distribution data, discrete point data, and CFD simulation data to the same parameter coordinate system; Calculate the deviation between the mapped discrete point data and the corresponding CFD simulation data of discrete points, and calculate the continuous deviation field of the occluded area based on the deviation. The CFD simulation data of discrete points in the shading area is corrected using the continuous deviation field, and the supplementary data is determined based on the corrected CFD simulation data of the discrete points. The supplementary data is used to characterize the heat transfer coefficient at locations other than the discrete points in the shading area. The complete data, discrete point data, and surface distribution data of the mapped unobstructed area are fused to obtain the heat transfer coefficient data of the entire turbine blade area.

2. The method according to claim 1, characterized in that, Acquire surface distribution data of the unobstructed area of ​​the turbine blades, discrete point data of the obstructed area, and CFD simulation data of the entire area, including: The heat transfer coefficient of the unshielded area of ​​the turbine blade was obtained as surface distribution data by using liquid crystal measurement of temperature-sensitive paint. The heat transfer coefficients of multiple preset discrete points in the shaded area are obtained using the copper block method as discrete point data. Computational fluid dynamics numerical simulation software was used to perform CFD simulations to obtain the heat transfer coefficient of the entire turbine blade region as CFD simulation data.

3. The method according to claim 1, characterized in that, Mapping the surface distribution data, discrete point data, and CFD simulation data to the same parametric coordinate system includes: A two-dimensional coordinate system is established along the blade height and arc length directions of the turbine blade, and the three-dimensional coordinates of each point on the turbine blade are parameterized based on the two-dimensional coordinate system to obtain the standardized coordinates of each point. The two-dimensional coordinate system is divided into a structured mesh to obtain a parametric coordinate system. Based on the parametric coordinate system, the parametric coordinates of each point on the turbine blade are determined, and the surface distribution data, discrete point data, and CFD simulation data corresponding to the parametric coordinates of each point are recorded.

4. The method according to claim 1, characterized in that, Calculate the deviation between the mapped discrete point data and the corresponding CFD simulation data, and calculate the continuous deviation field of the occluded region based on the deviation, including: For each discrete point within the occluded area, calculate the deviation between the discrete point data and the corresponding CFD simulation data; Based on the parameter coordinates and corresponding deviations of each discrete point, the continuous deviation field of the heat transfer coefficient in the shielded region is calculated using radial basis function interpolation.

5. The method according to claim 1, characterized in that, Based on the corrected discrete-point CFD simulation data, complete data is determined, including: Calculate the Euclidean distance between locations outside the discrete points in the occluded area and each discrete point, and determine the minimum Euclidean distance; The attenuation coefficient of the location outside the discrete point of the occluded area is determined by cross-validation, and the corrected weight of the location outside the discrete point of the occluded area is determined by weighting function based on the minimum Euclidean distance and the attenuation coefficient. Based on the corrected weights, CFD simulation data of discrete points, and CFD simulation data of corrected discrete points, the heat transfer coefficient at locations outside the discrete points in the shading area is calculated as the supplementary data.

6. The method according to claim 1, characterized in that, The completed data, discrete point data, and surface distribution data of the mapped unobstructed region are fused to obtain the heat transfer coefficient data of the entire turbine blade region, including: Using fluid dynamics physical constraints as a penalty term, the complete data, discrete point data, and surface distribution data of the mapped unobstructed region are fused and interpolated using the tightly supported radial basis function to obtain the continuously distributed heat transfer coefficient in the parametric coordinate system. By using surface reconstruction, the two-dimensional coordinates of the turbine blade in the parametric coordinate system are reconstructed into three-dimensional coordinates, and the continuously distributed heat transfer coefficients in the parametric coordinate system are mapped to the three-dimensional coordinate system to obtain the heat transfer coefficient data of the entire turbine blade region.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: In the unobstructed area, a preset number of data points are randomly obstructed, and the data completion values ​​of the preset number of points are completed using the data completion method of any one of claims 1 to 6 based on the remaining data in the area distribution data. Obtain the actual measurement values ​​of a preset number of points, and calculate the completion error based on the completion values ​​of the preset number of points and the actual measurement values, so as to verify the accuracy of the data completion method of any one of claims 1 to 6; The first measurement error of the unobstructed area, the second measurement error of the obstructed area, and the model uncertainty of the CFD simulation are obtained, and the uncertainty of the supplementary data is calculated based on the first measurement error, the second measurement error, and the model uncertainty.

8. A device for completing turbine blade heat transfer coefficient data based on multi-source data fusion, characterized in that, The device includes: The data mapping module is used to acquire surface distribution data of the unobstructed area of ​​the turbine blade, discrete point data of the obstructed area, and CFD simulation data of the entire area, and to map the surface distribution data, discrete point data, and CFD simulation data to the same parameter coordinate system. The deviation calculation module is used to calculate the deviation between the mapped discrete point data and the CFD simulation data of the corresponding discrete points, and to calculate the continuous deviation field of the occluded area based on the deviation. The data completion module is used to correct the CFD simulation data of discrete points in the shading area using the continuous deviation field, and to determine the completed data based on the corrected CFD simulation data of the discrete points. The completed data is used to characterize the heat transfer coefficient at locations other than the discrete points in the shading area. The multi-source data fusion module is used to fuse the completed data, discrete point data, and surface distribution data of the mapped non-obscured area to obtain the heat transfer coefficient data of the entire turbine blade area.

9. An electronic device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.

Images