Three-dimensional field cloud picture intelligent visualization method based on reduced-order model

Abstract

The invention relates to the technical field of image processing, in particular to a three-dimensional field cloud picture intelligent visualization method based on a reduced-order model. The method comprises the following steps: collecting a plurality of three-dimensional field data needing to generate a three-dimensional field cloud picture, cleaning different types of three-dimensional field data, converting the three-dimensional field data into a unified format, carrying out model training based on the three-dimensional field data with the unified format, and carrying out order reduction on the trained model to construct a three-dimensional order reduction model. Loading the created three-dimensional reduced-order model to output a three-dimensional field cloud picture, counting three-dimensional field data corresponding to the three-dimensional field cloud picture, judging the generated three-dimensional field cloud picture on the basis of the three-dimensional field data, generating a corresponding processing instruction on the basis of a judgment result, and re-determining operation parameters in the three-dimensional field cloud picture generation process on the basis of the received processing instruction. According to the invention, real-time monitoring and accurate regulation and control of the generated cloud picture are effectively realized, and the cloud picture generation efficiency is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to an intelligent visualization method for three-dimensional field cloud maps based on a reduced-order model. Background Art

[0002] Intelligent visualization of three-dimensional field cloud maps based on a reduced-order model is a method that combines a reduced-order model and intelligent visualization technology for efficient processing and intuitive display of three-dimensional field data. Three-dimensional field data refers to a data set that describes the distribution of a certain physical quantity or attribute in three-dimensional space. Three-dimensional field data is widely used in many fields such as scientific research, engineering calculations, weather forecasting, and geological exploration, and is the basis for quantitatively describing and analyzing various physical phenomena and processes in three-dimensional space. Intelligent visualization of three-dimensional field cloud maps based on a reduced-order model plays an important role in many fields such as aerospace, meteorological and climate research, biomedicine, and industrial manufacturing. It can present complex three-dimensional field data in an intuitive cloud map, and has important research significance in aspects such as improving decision-making efficiency, discovering potential laws, and optimizing designs and processes.

[0003] Chinese Patent Application Publication No.: CN114780771A discloses a method, device, electronic device, and storage medium for generating a digital twin of an environment. The method includes: obtaining a three-dimensional data set, a scene image, and environmental monitoring data; wherein, the three-dimensional data set includes scene three-dimensional data and physical object three-dimensional data; performing depth inference on the scene image to obtain a depth image; performing three-dimensional modeling on the scene image and the depth image to obtain a scene point cloud map; analyzing the scene three-dimensional data, the physical object three-dimensional data, and the scene point cloud map to obtain an environmental point cloud map; and combining the environmental point cloud map and the environmental monitoring data to obtain a digital twin result. According to the technical solution of the embodiment of the present invention, it is beneficial to perform visual monitoring and processing on the state data of the environment.

[0004] It can be seen that the above solution realizes visual monitoring and processing of the state data of the environment by obtaining an environmental point cloud map. However, the above solution cannot perform real-time monitoring and precise control on the generated cloud map, thus unable to ensure the generation efficiency of the cloud map. Summary of the Invention

[0005] Therefore, the present invention provides an intelligent visualization method for three-dimensional field cloud maps based on a reduced-order model to overcome the problem in the prior art that the generation efficiency of the cloud map is low because the generated cloud map cannot be monitored in real time and precisely controlled.

[0006] To achieve the above object, the present invention provides an intelligent visualization method for three-dimensional field cloud maps based on a reduced-order model, including: Collecting a number of three-dimensional field data for generating three-dimensional field cloud maps; Clean different types of the three-dimensional field data and convert them into a unified format; Perform model training based on the three-dimensional field data with unified format; Reduce the order of the trained model to construct a three-dimensional reduced-order model; Load the created three-dimensional reduced-order model to output a three-dimensional field cloud map; Statistical the three-dimensional field data corresponding to the three-dimensional field cloud map; Make a determination for the generated three-dimensional field cloud map based on the three-dimensional field data; Generate corresponding processing instructions based on the determination result, Or, complete the determination of the three-dimensional field cloud map and implement the interaction between the three-dimensional field cloud map and the user; Among them, the determination includes determining whether the three-dimensional field cloud map meets the standard and the reasons for not meeting the standard; Re-determine the operating parameters in the generation process of the three-dimensional field cloud map based on the received processing instructions.

[0007] Further, the process of making a determination for the generated three-dimensional field cloud map based on the three-dimensional field data includes: Randomly select the three-dimensional field data corresponding to the three-dimensional field cloud map; Determine the preset three-dimensional field cloud map corresponding to the three-dimensional field cloud map, and obtain the preset three-dimensional field data corresponding to the randomly selected three-dimensional field data; For a single three-dimensional field data, calculate the difference between the three-dimensional field data and the corresponding preset three-dimensional field data, and record the obtained difference as the relative error for the three-dimensional field data; Successively complete the calculation of the relative errors of each randomly selected three-dimensional field data; Calculate the average value of the relative errors, and record the obtained average value as the average relative error; Make a determination for the generated three-dimensional field cloud map based on the average relative error; When the average relative error is less than the first preset average relative error, determine that the three-dimensional field cloud map meets the standard, complete the determination of the three-dimensional field cloud map, and implement the interaction between the three-dimensional field cloud map and the user; When the average relative error is greater than or equal to the first preset average relative error and less than the second preset average relative error, determine that the three-dimensional field cloud map does not meet the standard, and make a determination for the generated three-dimensional field cloud map based on the total amount of the three-dimensional field data; When the average relative error is greater than or equal to the second preset average relative error, determine that the three-dimensional field cloud map does not meet the standard, and determine the reasons for the three-dimensional field cloud map not meeting the standard based on the average relative error.

[0008] Further, the process of determining the generated three-dimensional field cloud map based on the total amount of the three-dimensional field data includes: Determine the total amount of the three-dimensional field data for generating the three-dimensional field cloud map, and record the obtained total amount of data as the total amount of three-dimensional field data; Calculate the generation duration for generating the three-dimensional field cloud map based on the total amount of the three-dimensional field data, and the reduced-order generation duration for generating the three-dimensional field cloud map based on the three-dimensional reduced-order model; Calculate the ratio of the reduced-order generation duration to the generation duration, and record the obtained ratio as the time-consuming ratio; Make a determination on the generated three-dimensional field data based on the time-consuming ratio; When the time-consuming ratio is greater than the preset time-consuming ratio, determine that the three-dimensional field cloud map meets the standard, and increase the number of main modes used in the reduced-order process based on the time-consuming ratio; When the time-consuming ratio is less than or equal to the preset time-consuming ratio, determine that the three-dimensional field cloud map does not meet the standard, and determine the reason why the three-dimensional field cloud map does not meet the standard based on the average value of the relative errors.

[0009] Further, the process of increasing the number of the main modes used in the reduced-order process based on the time-consuming ratio includes: Calculate the difference between the time-consuming ratio and the preset time-consuming ratio, and record the obtained difference as the time-consuming ratio difference; Increase the number of the main modes used in the reduced-order process based on the time-consuming ratio difference, and the increase amplitude of the number of main modes is proportional to the time-consuming ratio.

[0010] Further, the process of determining the reason why the three-dimensional field cloud map does not meet the standard based on the average value of the relative errors includes: Calculate the difference between the average value of the relative errors and the second preset average value of the relative errors, and record the obtained difference as the average value difference of the errors; Determine the reason why the three-dimensional field cloud map does not meet the standard based on the average value difference of the errors; When the average value difference of the errors is less than the first preset average value difference of the errors, determine whether the output of the three-dimensional field cloud map meets the standard based on the variance of the relative errors; When the average value difference of the errors is greater than or equal to the first preset average value difference of the errors and less than the second preset average value difference of the errors, determine whether the reduced-order of the model meets the standard based on the historical average value of the relative errors; When the difference between the average errors is greater than or equal to the second preset difference between the average errors, it is determined that the reason for the non - compliance of the 3D field cloud map with the standard is that the collection of the 3D field data does not meet the standard, and the number of the collected 3D field data is corrected based on the difference between the average errors.

[0011] Further, the process of determining whether the output of the 3D field cloud map meets the standard based on the variance of the relative error includes: Calculate the variance of the relative error, and denote the obtained variance as the error variance; Determine whether the output of the 3D field cloud map meets the standard based on the error variance; When the error variance is less than or equal to the preset error variance, it is determined that the integrity of the 3D field cloud map does not meet the standard, and a notice of abnormal output of the 3D field cloud map is issued; When the error variance is greater than the preset error variance, determine whether the order reduction of the model meets the standard based on the historical average value of the relative error.

[0012] Further, the process of determining whether the order reduction of the model meets the standard based on the historical average value of the relative error includes: Obtain the historical average value of the relative error, and construct a time - relative error average value curve based on the historical average value of the relative error and the average value of the relative error; Calculate the integral value of the curve, and denote the obtained integral value as the curve integral value; Determine whether the order reduction of the model meets the standard based on the curve integral value; When the curve integral value is greater than the preset curve integral value, determine whether the order reduction of the model meets the standard based on the slope of the curve at each time node; When the curve integral value is less than or equal to the preset curve integral value, it is determined that the reason for the non - compliance of the 3D field cloud map with the standard is that the collection of the 3D field data does not meet the standard, and the number of the collected 3D field data is corrected based on the difference between the average errors.

[0013] Further, the process of determining whether the order reduction of the model meets the standard based on the slope of the curve at each time node includes: Determine the absolute value of the slope of the curve at each time node, and denote the obtained slope as the node slope; Calculate the average value of each of the node slopes, and denote the obtained average value as the average node slope; Determine whether the order reduction of the model meets the standard based on the average node slope; When the average node slope is less than or equal to the preset average node slope, it is determined that the order reduction of the model does not meet the standard, and the standard for removing redundant data in the process of model order reduction is corrected based on the average node slope; When the average value of the node slopes is greater than the preset average value of the node slopes, it is determined that the order reduction of the model meets the standard, the collection of the three-dimensional field data does not meet the standard, and the number of the collected three-dimensional field data is corrected based on the difference in the average error value.

[0014] Further, the process of correcting the standard for removing the redundant data during the model training process based on the average value of the node slopes includes: Calculate the ratio of the average value of the node slopes to the preset average value of the node slopes, and denote the obtained ratio as the node slope ratio; Based on the node slope ratio, increase the standard for removing the redundant data, and the increase amplitude of the standard for removing the redundant data is proportional to the node slope ratio.

[0015] Further, the process of correcting the number of the collected three-dimensional field data based on the difference in the average error value includes: Increase the number of the collected three-dimensional field data based on the average error value, and the increase amplitude of the number of the three-dimensional data is proportional to the average error value.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows. By statistically analyzing the three-dimensional field data corresponding to the three-dimensional field cloud map and making a determination on the generated three-dimensional field cloud map based on the three-dimensional field data, the present invention can complete the determination of the generated three-dimensional field cloud map in a timely and accurate manner. The determination includes determining whether the three-dimensional field cloud map meets the standard and determining the reasons for not meeting the standard, effectively realizing the real-time monitoring of the generated cloud map, generating corresponding processing instructions based on the determination results, and re-determining the operating parameters during the generation process of the three-dimensional field cloud map based on the received processing instructions. While effectively realizing the precise regulation of the generated cloud map, the present invention effectively improves the generation efficiency of the cloud map.

[0017] Further, by making a determination on the generated three-dimensional field cloud map based on the relative average error value, the present invention can accurately determine whether the three-dimensional field cloud map meets the standard based on the three-dimensional field data corresponding to the three-dimensional field cloud map. While further realizing the real-time monitoring of the generated cloud map, the present invention further improves the generation efficiency of the cloud map.

[0018] Further, when the relative average error value is greater than or equal to the first preset relative average error value and less than the second preset relative average error value, the present invention makes a determination on the generated three-dimensional field data based on the time-consuming ratio, avoiding the occurrence of misjudgment. While further realizing the real-time monitoring of the generated cloud map, the present invention further improves the generation efficiency of the cloud map.

[0019] Furthermore, when the time-consuming ratio is greater than the preset time-consuming ratio, the present invention increases the number of main modes used in the order reduction process based on the time-consuming ratio difference, effectively avoiding the occurrence of the situation that the three-dimensional field cloud map does not meet the standard due to the number of main modes not meeting the standard. While further realizing the precise regulation of the generated cloud map, the generation efficiency of the cloud map is further improved.

[0020] Furthermore, the present invention determines the reason why the three-dimensional field cloud map does not meet the standard based on the error average difference value, and can timely and accurately complete the determination of the reason for not meeting the standard. While further realizing the real-time monitoring of the generated cloud map, the generation efficiency of the cloud map is further improved.

[0021] Furthermore, when the error average difference value is less than the first preset error average difference value, the present invention determines whether the output of the three-dimensional field cloud map meets the standard based on the error variance, effectively avoiding misjudgment between the integrity of the three-dimensional field cloud map not meeting the standard and the order reduction of the model not meeting the standard. While further realizing the real-time monitoring of the generated cloud map, the generation efficiency of the cloud map is further improved.

[0022] Furthermore, when the error average difference value is greater than or equal to the first preset error average difference value and less than the second preset error average difference value, the present invention determines whether the order reduction of the model meets the standard based on the curve integral value, effectively avoiding misjudgment between the collection of three-dimensional field data not meeting the standard and the need to determine whether the order reduction of the model meets the standard. While further realizing the real-time monitoring of the generated cloud map, the generation efficiency of the cloud map is further improved.

[0023] Furthermore, when the curve integral value is greater than the preset curve integral value, the present invention determines whether the order reduction of the model meets the standard based on the average node slope, effectively avoiding misjudgment between the order reduction of the model not meeting the standard and the collection of three-dimensional field data not meeting the standard. While further realizing the real-time monitoring of the generated cloud map, the generation efficiency of the cloud map is further improved.

[0024] Furthermore, when it is determined that the order reduction of the model does not meet the standard, the present invention increases the standard for removing redundant data based on the node slope ratio, effectively avoiding the occurrence of the situation that the three-dimensional field cloud map does not meet the standard due to the standard for removing redundant data not meeting the standard. While further realizing the precise regulation of the generated cloud map, the generation efficiency of the cloud map is further improved.

[0025] Furthermore, when the present invention determines that the collection of three-dimensional field data does not meet the standard, it increases the quantity of the collected three-dimensional field data based on the average error, effectively avoiding the occurrence of the situation where the three-dimensional field cloud map does not meet the standard due to the quantity of the collected three-dimensional field data not meeting the standard. While further realizing the precise regulation of the generated cloud map, it further improves the generation efficiency of the cloud map. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a structural block diagram of an intelligent visualization system for three-dimensional field cloud maps based on a reduced-order model according to an embodiment of the present invention; Figure 2 is a flowchart of an intelligent visualization method for three-dimensional field cloud maps based on a reduced-order model according to an embodiment of the present invention; Figure 3 is a flowchart for determining whether a three-dimensional field cloud map meets the standard according to an embodiment of the present invention; Figure 4 is a flowchart for determining the reasons why a three-dimensional field cloud map does not meet the standard according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] In order to make the objectives and advantages of the present invention clearer and more understandable, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0028] Next, the preferred embodiments of the present invention will be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0029] In addition, it should be noted that in the description of the present invention, unless otherwise clearly defined and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0030] Please refer to Figure 1 shown, which is a structural block diagram of an intelligent visualization system for three-dimensional field cloud maps based on a reduced-order model according to an embodiment of the present invention. The structure of the embodiment of the present invention includes a collection module, a processing module, a training module, a reduced-order module, a generation module, an analysis module, and a control module; among them, the collection module is used to collect a number of three-dimensional field data required to generate three-dimensional field cloud maps; The processing module is connected to the acquisition module for cleaning different types of the three-dimensional field data and converting them into a unified format; The training module is connected to the processing module for model training based on the three-dimensional field data with a unified format; The order reduction module is connected to the training module for reducing the order of the trained model to construct a three-dimensional reduced-order model; The generation module is connected to the order reduction module for loading the created three-dimensional reduced-order model to output a three-dimensional field cloud map; The analysis module is connected to the generation module for counting the three-dimensional field data corresponding to the three-dimensional field cloud map; The analysis module is also used for making a determination on the generated three-dimensional field cloud map based on the three-dimensional field data; The analysis module is also used for generating corresponding processing instructions based on the determination result, or, completing the determination of the three-dimensional field cloud map and realizing the interaction between the three-dimensional field cloud map and the user; wherein, the determination includes determining whether the three-dimensional field cloud map meets the standard and the reasons for not meeting the standard; The control module is respectively connected to the collection module, the order reduction module and the analysis module for re-determining the operation parameters in the generation process of the three-dimensional field cloud map based on the received processing instructions.

[0031] Please refer to Figure 2 As shown, it is a flowchart of the intelligent visualization method of the three-dimensional field cloud map based on the reduced-order model in an embodiment of the present invention. The method in the embodiment of the present invention includes: Collect a number of three-dimensional field data required to generate a three-dimensional field cloud map; Clean different types of the three-dimensional field data and convert them into a unified format; Perform model training based on the three-dimensional field data with a unified format; Reduce the order of the trained model to construct a three-dimensional reduced-order model; Load the created three-dimensional reduced-order model to output a three-dimensional field cloud map; Count the three-dimensional field data corresponding to the three-dimensional field cloud map; Make a determination on the generated three-dimensional field cloud map based on the three-dimensional field data; Generate corresponding processing instructions based on the determination result, or, complete the determination of the three-dimensional field cloud map and realize the interaction between the three-dimensional field cloud map and the user; wherein, the determination includes determining whether the three-dimensional field cloud map meets the standard and the reasons for not meeting the standard; Re-determine the operation parameters in the generation process of the three-dimensional field cloud map based on the received processing instructions.

[0032] Please refer to Figure 3 as shown, which is a flowchart for determining whether the three-dimensional field cloud map meets the standard in an embodiment of the present invention. The process of determining the generated three-dimensional field cloud map based on the three-dimensional field data in the embodiment of the present invention includes: Randomly select the three-dimensional field data corresponding to the three-dimensional field cloud map; Determine the preset three-dimensional field cloud map corresponding to the three-dimensional field cloud map, and obtain the preset three-dimensional field data corresponding to the randomly selected three-dimensional field data; For a single piece of the three-dimensional field data, calculate the difference between the three-dimensional field data and the corresponding preset three-dimensional field data, and record the obtained difference as the relative error for the three-dimensional field data; Successively complete the calculation of the relative errors of each of the randomly selected three-dimensional field data; Calculate the average value of the relative errors, and record the obtained average value as the average relative error; Based on the average relative error, determine the generated three-dimensional field cloud map; When the average relative error is less than the first preset average relative error E1, it is determined that the three-dimensional field cloud map meets the standard, the determination of the three-dimensional field cloud map is completed, and the interaction between the three-dimensional field cloud map and the user is realized. Wherein, in this embodiment, the first preset average relative error E1 = 0.017; When the average relative error is greater than or equal to the first preset average relative error E1 and less than the second preset average relative error E2, it is determined that the three-dimensional field cloud map does not meet the standard, and the generated three-dimensional field cloud map is determined based on the total amount of the three-dimensional field data. Wherein, in this embodiment, the second preset average relative error E2 = 0.283; When the average relative error is greater than or equal to the second preset average relative error E2, it is determined that the three-dimensional field cloud map does not meet the standard, and the reason why the three-dimensional field cloud map does not meet the standard is determined based on the average relative error; Specifically, the preset three-dimensional field cloud map is selected from the test set, the three-dimensional field data is calculated from the preset data, and the preset three-dimensional field data corresponds to the preset data.

[0033] Please continue to refer to Figure 3 as shown, the process of determining the generated three-dimensional field cloud map based on the total amount of the three-dimensional field data in the embodiment of the present invention includes: Determine the total amount of the three-dimensional field data for generating the three-dimensional field cloud map, and record the obtained total amount as the total amount of the three-dimensional field data; Calculate the generation duration for generating the 3D field cloud map based on the total amount of the 3D field data, and the reduced-order generation duration for generating the 3D field cloud map based on the 3D reduced-order model; Calculate the ratio of the reduced-order generation duration to the generation duration, and denote the obtained ratio as the time-consuming ratio; Make a determination on the generated 3D field data based on the time-consuming ratio; When the time-consuming ratio is greater than the preset time-consuming ratio T, determine that the 3D field cloud map meets the standard, and increase the number of dominant modes used in the reduced-order process based on the time-consuming ratio, where the preset time-consuming ratio T = 2.857 in this embodiment; When the time-consuming ratio is less than or equal to the preset time-consuming ratio T, determine that the 3D field cloud map does not meet the standard, and determine the reason why the 3D field cloud map does not meet the standard based on the average relative error; Specifically, during the process of reducing the order of the trained model to construct the 3D reduced-order model, redundant data is removed during the reduction, and the dominant modes are extracted to construct the 3D reduced-order model.

[0034] Please continue to refer to Figure 3 As shown, the process of increasing the number of the dominant modes used in the reduced-order process based on the time-consuming ratio in the embodiment of the present invention includes: Calculate the difference between the time-consuming ratio and the preset time-consuming ratio, and denote the obtained difference as the time-consuming ratio difference; Increase the number of the dominant modes used in the reduced-order process based on the time-consuming ratio difference; When the time-consuming ratio difference is greater than the second preset time-consuming ratio difference △D2, increase the number of the dominant modes to 1.63 times the initial number of the dominant modes, where the second preset time-consuming ratio difference △D2 = 0.457 in the embodiment of the present invention; When the time-consuming ratio difference is less than or equal to the second preset time-consuming ratio difference △D2 and greater than the first preset time-consuming ratio difference △D1, increase the number of the dominant modes to 1.48 times the initial number of the dominant modes, where the first preset time-consuming ratio difference △D1 = 0.218 in the embodiment of the present invention; When the time-consuming ratio difference is less than or equal to the first preset time-consuming ratio difference △D1, increase the number of the dominant modes to 1.29 times the initial number of the dominant modes.

[0035] Please refer to Figure 4 As shown, it is a flowchart of the reason for determining that the 3D field cloud map does not meet the standard in the embodiment of the present invention. The process of determining the reason why the 3D field cloud map does not meet the standard based on the average relative error in the embodiment of the present invention includes: Calculate the difference between the average relative error and the second preset average relative error, and denote the obtained difference as the average error difference; Determine the reason why the 3D field cloud map does not meet the standard based on the difference in the average error values; When the difference in the average error values is less than the first preset difference in the average error value △V1, determine whether the output of the 3D field cloud map meets the standard based on the variance of the relative error, where the first preset difference in the average error value △V1 = 0.0213 in the embodiments of the present invention; When the difference in the average error values is greater than or equal to the first preset difference in the average error value △V1 and less than the second preset difference in the average error value △V2, determine whether the reduction of the historical relative error average value determination model meets the standard, where the second preset difference in the average error value △V2 = 0.0589 in the embodiments of the present invention; When the difference in the average error values is greater than or equal to the second preset difference in the average error value △V2, determine that the reason why the 3D field cloud map does not meet the standard is that the collection of the 3D field data does not meet the standard, and correct the quantity of the collected 3D field data based on the difference in the average error values.

[0036] Please continue to refer to Figure 4 As shown, the process of determining whether the output of the 3D field cloud map meets the standard based on the variance of the relative error in the embodiments of the present invention includes: Calculate the variance of the relative error, and denote the obtained variance as the error variance; Determine whether the output of the 3D field cloud map meets the standard based on the error variance; When the error variance is less than or equal to the preset error variance C, determine that the integrity of the 3D field cloud map does not meet the standard, and send a notice of abnormal output of the 3D field cloud map, where the preset average error variance C = 0.0007 in the embodiments of the present invention; When the error variance is greater than the preset error variance C, determine whether the reduction of the historical relative error average value determination model meets the standard.

[0037] Please continue to refer to Figure 4 As shown, the process of determining whether the reduction of the historical relative error average value determination model meets the standard in the embodiments of the present invention includes: Obtain the historical relative error average value, and construct a time-relative error average value curve based on the historical relative error average value and the relative error average value; Calculate the integral value of the curve, and denote the obtained integral value as the curve integral value; Determine whether the reduction of the model meets the standard based on the curve integral value; When the curve integral value is greater than the preset curve integral value G, determine whether the reduction of the model meets the standard based on the slope of the curve at each time node, where the preset curve integral value G = 4.218 in the embodiments of the present invention; When the value of the line integral is less than or equal to the preset line integral value G, it is determined that the reason for the non - compliance of the three - dimensional field cloud map with the standard is that the collection of the three - dimensional field data does not meet the standard, and the number of the collected three - dimensional field data is corrected based on the difference in the average error values; Specifically, the historical average relative error is the first 9 average relative error values of the average relative error.

[0038] Please continue to refer to Figure 4 As shown, the process of determining whether the order reduction of the model based on the slope of the curve at each time node in the embodiment of the present invention meets the standard includes: Determine the absolute value of the slope of the curve at each time node, and denote the obtained slope as the node slope; Calculate the average value of each of the node slopes, and denote the obtained average value as the average node slope; Determine whether the order reduction of the model meets the standard based on the average node slope; When the average node slope is less than or equal to the preset average node slope value N, it is determined that the order reduction of the model does not meet the standard, and the standard for removing redundant data in the model order reduction process is corrected based on the average node slope, where the preset average node slope value N = 1.23 in the embodiment of the present invention; When the average node slope is greater than the preset average node slope value N, it is determined that the order reduction of the model meets the standard, the collection of the three - dimensional field data does not meet the standard, and the number of the collected three - dimensional field data is corrected based on the difference in the average error values; Specifically, in the process of removing the redundant data during order reduction, the data is subjected to correlation analysis and the correlation coefficient between the data is calculated. The data with a correlation coefficient greater than the redundant data standard S is removed, the data with a variance less than 18.3% of the overall variance average is removed, and the data with an impact on the model output less than 4.7% is removed, where the redundant data standard S is 0.82.

[0039] Please continue to refer to Figure 4 As shown, the process of correcting the standard for removing the redundant data in the model training process based on the average node slope in the embodiment of the present invention includes: Calculate the ratio of the average node slope to the preset average node slope, and denote the obtained ratio as the node slope ratio; Increase the standard for removing the redundant data based on the node slope ratio; When the node slope ratio is greater than the second preset node slope ratio R2, increase the standard for removing the redundant data to 1.178 times the initial standard for removing redundant data, where the second preset node slope ratio R2 = 91.06% in the embodiment of the present invention; When the node ratio difference is less than or equal to the second preset node slope ratio R2 and greater than the first preset node slope ratio R1, increase the standard for removing redundant data to 1.121 times the initial standard for removing redundant data, where the first preset node slope ratio R1 = 85.37% in the embodiments of the present invention; When the node ratio difference is less than or equal to the first preset node slope ratio R1, increase the standard for removing redundant data to 1.063 times the initial standard for removing redundant data.

[0040] Please continue to refer to Figure 4 As shown, the process of correcting the quantity of the collected three-dimensional field data based on the error average difference in the embodiments of the present invention includes: Increase the quantity of the collected three-dimensional field data based on the error average; When the error average difference is greater than the second preset error average difference △A2, increase the quantity of the collected three-dimensional field data to 1.57 times the initial quantity of the collected three-dimensional field data, where the second preset error average difference △A2 = 0.1359 in the embodiments of the present invention; When the error average difference is less than or equal to the second preset error average difference △A2 and greater than the first preset error average difference △A1, increase the quantity of the collected three-dimensional field data to 1.39 times the initial quantity of the collected three-dimensional field data, where the first preset error average difference △A1 = 0.0571 in the embodiments of the present invention; When the error average difference is less than or equal to the first preset error average difference △A1, increase the quantity of the collected three-dimensional field data to 1.26 times the initial quantity of the collected three-dimensional field data.

[0041] Embodiment 1: When collecting three-dimensional field data for generating a three-dimensional field cloud map of temperature during the exterior design of an automobile, the three-dimensional field data includes design parameters and experimental data of the automobile, etc. Clean the collected different types of data to remove abnormal data, and convert them into a unified format. Based on the three-dimensional field data with unified format, perform model training, reduce the order of the trained model, remove redundant data and extract the main mode to construct a three-dimensional reduced-order model, load the created three-dimensional reduced-order model to output a three-dimensional field cloud map, and optimize the exterior design of the automobile through the three-dimensional field cloud map.

[0042] Randomly select the three-dimensional field data corresponding to 11 three-dimensional field cloud maps, determine the preset three-dimensional field data. For a single three-dimensional field data, calculate the difference between this three-dimensional field data and the corresponding preset three-dimensional field data, which is denoted as the relative error for this three-dimensional field data. Sequentially complete the calculation of the relative errors of the 11 randomly selected three-dimensional field data. The 11 relative errors are 0.19, 0.22, 0.21, 0.12, 0.25, 0.11, 0.23, 0.17, 0.16, 0.24, and 0.22 respectively. Calculate the average value of each relative error, which is denoted as the average relative error. The average relative error is 0.1927, which is greater than or equal to the first preset average relative error of 0.017 and less than the second preset average relative error of 0.283. Determine the total amount of the three-dimensional field data for generating the three-dimensional field cloud map, which is denoted as the total amount of three-dimensional field data. Calculate the generation duration for generating the three-dimensional field cloud map based on the total amount of three-dimensional field data. The generation duration is 8.92 min. Calculate the reduced-order generation duration for generating the three-dimensional field cloud map based on the three-dimensional reduced-order model. The reduced-order generation duration is 2.87 min. Calculate the ratio of the reduced-order generation duration to the generation duration, which is denoted as the time-consuming ratio. The time-consuming ratio is 3.108, which is greater than the preset time-consuming ratio of 2.857. Calculate the difference between the time-consuming ratio of 3.108 and the preset time-consuming ratio of 2.857, which is denoted as the time-consuming ratio difference. The time-consuming ratio difference is 0.251, which is less than or equal to the second preset time-consuming ratio difference of 0.457 and greater than the first preset time-consuming ratio difference of 0.218. Increase the number of main modes to 1.48 times the initial number of main modes.

[0043] Example 2: Collect the three-dimensional field data required to generate a three-dimensional field cloud map of temperature during aircraft engine thermal management. The three-dimensional field data includes temperature data during the operation of the aircraft engine, aircraft engine speed, aircraft fuel quantity data, etc. Clean the collected different types of data to remove abnormal data and convert them into a unified format. Based on the three-dimensional field data with unified format, conduct model training. Reduce the order of the trained model, remove redundant data and extract the main modes to construct a three-dimensional reduced-order model. Load the created three-dimensional reduced-order model to output the three-dimensional field cloud map, visually display the temperature distribution of the internal components of the aircraft, and monitor and optimize the aircraft engine thermal management in real time to help engineers quickly locate high-temperature areas and cooling abnormal parts and adjust strategies in a timely manner.

[0044] Randomly select the 3D field data corresponding to 27 3D field cloud maps, determine the preset 3D field data. For a single 3D field data, calculate the difference between this 3D field data and the corresponding preset 3D field data, which is denoted as the relative error for this 3D field data. Sequentially complete the calculation of the relative errors of the randomly selected 27 3D field data. The 27 relative errors are 0.37, 0.29, 0.27, 0.32, 0.38, 0.18, 0.33, 0.47, 0.56, 0.34, 0.28, 0.31, 0.32, 0.35, 0.33, 0.34, 0.31, 0.39, 0.35, 0.27, 0.28, 0.31, 0.39, 0.42, 0.27, 0.38, and 0.35 respectively. Calculate the average value of each relative error, which is denoted as the average relative error. The average relative error is 0.3392, which is greater than or equal to the second preset average relative error of 0.283. Calculate the difference between the average relative error of 0.3392 and the second preset average relative error of 0.283, which is denoted as the difference in average error. The difference in average error is 0.0562, which is greater than or equal to the first preset difference in average error of 0.0213 and less than the second preset difference in average error of 0.0589. Determine whether the order reduction of the historical relative error average value determination model meets the standard, obtain the historical relative error average value, and construct a time-average relative error curve based on the historical relative error average value and the average relative error. Calculate the integral value of the curve, which is denoted as the curve integral value. The curve integral value is 5.879, which is greater than the preset curve integral value of 4.218. Determine the absolute value of the slope of the curve at each time node, which is denoted as the node slope. Calculate the average value of each node slope, which is denoted as the average node slope. The average node slope is 1.298, which is greater than the preset average node slope of 1.23. Increase the number of 3D field data collected based on the average error. The difference in average error is 0.0562, which is less than or equal to the first preset difference in average error of 0.0571. Increase the number of 3D field data collected to 1.26 times the number of the initially collected 3D field data.

[0045] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0046] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent visualization method for three-dimensional field cloud maps based on a reduced-order model, characterized in that, Including: Collecting a number of three-dimensional field data for generating three-dimensional field cloud maps; Cleaning different types of the three-dimensional field data and converting them into a unified format; Performing model training based on the three-dimensional field data with unified format; Reducing the order of the trained model to construct a three-dimensional reduced-order model; Loading the created three-dimensional reduced-order model to output a three-dimensional field cloud map; Counting the three-dimensional field data corresponding to the three-dimensional field cloud map; Making a determination for the generated three-dimensional field cloud map based on the three-dimensional field data; Generating corresponding processing instructions based on the determination result, or, completing the determination of the three-dimensional field cloud map and realizing the interaction between the three-dimensional field cloud map and the user; wherein, the determination includes determining whether the three-dimensional field cloud map meets the standard and the reasons for not meeting the standard; Re-determining the operating parameters in the process of generating the three-dimensional field cloud map based on the received processing instructions.

2. The intelligent visualization method of the three-dimensional field cloud map based on the reduced-order model according to claim 1, characterized in that The process of making a determination for the generated three-dimensional field cloud map based on the three-dimensional field data includes: Randomly selecting the three-dimensional field data corresponding to the three-dimensional field cloud map; Determining a preset three-dimensional field cloud map corresponding to the three-dimensional field cloud map, and obtaining preset three-dimensional field data corresponding to the randomly selected three-dimensional field data; For a single piece of the three-dimensional field data, calculating the difference between the three-dimensional field data and the corresponding preset three-dimensional field data, and recording the obtained difference as the relative error for the three-dimensional field data; Sequentially completing the calculation of the relative errors of each piece of the randomly selected three-dimensional field data; Calculating the average value of the relative errors, and recording the obtained average value as the average relative error; Making a determination for the generated three-dimensional field cloud map based on the average relative error; When the average relative error is less than the first preset average relative error, determining that the three-dimensional field cloud map meets the standard, completing the determination of the three-dimensional field cloud map, and realizing the interaction between the three-dimensional field cloud map and the user; When the average relative error is greater than or equal to the first preset average relative error and less than the second preset average relative error, determining that the three-dimensional field cloud map does not meet the standard, and making a determination for the generated three-dimensional field cloud map based on the total amount of the three-dimensional field data; When the average relative error is greater than or equal to the second preset average relative error, determining that the three-dimensional field cloud map does not meet the standard, and determining the reasons for the three-dimensional field cloud map not meeting the standard based on the average relative error.

3. The intelligent visualization method of 3D field cloud map based on the reduced-order model according to claim 2, characterized in that, The process of making a determination for the generated three-dimensional field cloud map based on the total amount of the three-dimensional field data includes: Determining the total amount of the three-dimensional field data for generating the three-dimensional field cloud map, and recording the obtained total amount as the total amount of three-dimensional field data; Calculating the generation duration for generating the three-dimensional field cloud map based on the total amount of the three-dimensional field data, and the reduced-order generation duration for generating the three-dimensional field cloud map based on the three-dimensional reduced-order model; Calculating the ratio of the reduced-order generation duration to the generation duration, and recording the obtained ratio as the time-consuming ratio; Making a determination for the generated three-dimensional field data based on the time-consuming ratio; When the time-consuming ratio is greater than the preset time-consuming ratio, it is determined that the three-dimensional field cloud map meets the standard, and the number of main modes used in the reduction process is increased based on the time-consuming ratio; When the time-consuming ratio is less than or equal to the preset time-consuming ratio, it is determined that the three-dimensional field cloud map does not meet the standard, and the reason why the three-dimensional field cloud map does not meet the standard is determined based on the average relative error.

4. The intelligent visualization method of three-dimensional field cloud map based on the reduced-order model according to claim 3, wherein The process of increasing the number of the main modes used in the reduction process based on the time-consuming ratio includes: Calculate the difference between the time-consuming ratio and the preset time-consuming ratio, and record the obtained difference as the time-consuming ratio difference; Increase the number of the main modes used in the reduction process based on the time-consuming ratio difference, and the increase amplitude of the number of main modes is proportional to the time-consuming ratio.

5. The intelligent visualization method of three-dimensional field cloud map based on the reduced-order model according to claim 3, characterized in that The process of determining the reason why the three-dimensional field cloud map does not meet the standard based on the average relative error includes: Calculate the difference between the average relative error and the second preset average relative error, and record the obtained difference as the average error value difference; Determine the reason why the three-dimensional field cloud map does not meet the standard based on the average error value difference; When the average error value difference is less than the first preset average error value difference, determine whether the output of the three-dimensional field cloud map meets the standard based on the variance of the relative error; When the average error value difference is greater than or equal to the first preset average error value difference and less than the second preset average error value difference, determine whether the reduction of the model meets the standard based on the historical average relative error; When the average error value difference is greater than or equal to the second preset average error value difference, it is determined that the reason why the three-dimensional field cloud map does not meet the standard is that the collection of the three-dimensional field data does not meet the standard, and the number of the collected three-dimensional field data is corrected based on the average error value difference.

6. The intelligent visualization method of three-dimensional field cloud map based on the reduced-order model according to claim 5, characterized in that, The process of determining whether the output of the three-dimensional field cloud map meets the standard based on the variance of the relative error includes: Calculate the variance of the relative error, and record the obtained variance as the error variance; Determine whether the output of the three-dimensional field cloud map meets the standard based on the error variance; When the error variance is less than or equal to the preset error variance, it is determined that the integrity of the three-dimensional field cloud map does not meet the standard, and a notice of abnormal output of the three-dimensional field cloud map is issued; When the error variance is greater than the preset error variance, determine whether the reduction of the model meets the standard based on the historical average relative error.

7. The intelligent visualization method for three-dimensional field cloud map based on the reduced-order model according to claim 6, wherein The process of determining whether the reduction of the model meets the standard based on the historical average relative error includes: Obtain the historical average relative error, and construct a time-average relative error curve based on the historical average relative error and the average relative error; Calculate the integral value of the curve, and record the obtained integral value as the curve integral value; Determine whether the reduction of the model meets the standard based on the curve integral value; When the curve integral value is greater than the preset curve integral value, determine whether the reduction of the model meets the standard based on the slope of the curve at each time node; When the value of the line integral is less than or equal to the preset line integral value, it is determined that the reason for the non - compliance of the three - dimensional field cloud map with the standard is that the collection of the three - dimensional field data does not meet the standard, and the number of the collected three - dimensional field data is corrected based on the difference in the average error value.

8. The intelligent visualization method of 3D field cloud map based on reduced-order model according to claim 7, characterized in that, The process of determining whether the order reduction of the model meets the standard based on the slope of the curve at each time node includes: Determine the absolute value of the slope of the curve at each time node, and denote the obtained slope as the node slope; Calculate the average value of each of the node slopes, and denote the obtained average value as the average node slope; Determine whether the order reduction of the model meets the standard based on the average node slope; When the average node slope is less than or equal to the preset average node slope, it is determined that the order reduction of the model does not meet the standard, and the standard for removing redundant data in the model order reduction process is corrected based on the average node slope; When the average node slope is greater than the preset average node slope, it is determined that the order reduction of the model meets the standard, the collection of the three - dimensional field data does not meet the standard, and the number of the collected three - dimensional field data is corrected based on the difference in the average error value.

9. The intelligent visualization method of three-dimensional field cloud map based on reduced-order model according to claim 8, characterized in that, The process of correcting the standard for removing the redundant data in the model training process based on the average node slope includes: Calculate the ratio of the average node slope to the preset average node slope, and denote the obtained ratio as the node slope ratio; Increase the standard for removing the redundant data based on the node slope ratio, and the increase amplitude of the standard for removing redundant data is proportional to the node slope ratio.

10. The intelligent visualization method of three-dimensional field cloud map based on the reduced-order model according to claim 8, characterized in that, The process of correcting the number of the collected three - dimensional field data based on the difference in the average error value includes: Increase the number of the collected three - dimensional field data based on the average error value, and the increase amplitude of the number of the three - dimensional data is proportional to the average error value.

Images