Vehicle type performance boundary analysis method, device and equipment and storage medium

Abstract

The invention discloses a vehicle type performance boundary analysis method, device and equipment and a storage medium, relates to the technical field of data processing, and discloses a vehicle type performance boundary analysis method comprising the following steps: obtaining a performance boundary training data set; performing clustering analysis on the performance boundary training data set to obtain a to-be-matched performance cluster; matching performance parameters of a to-be-analyzed vehicle model with the to-be-matched performance cluster to obtain a target performance cluster to which the to-be-analyzed vehicle model belongs; and determining a performance boundary of the to-be-analyzed vehicle model based on the target performance cluster. According to the scheme, the vehicle type performance boundary can be efficiently and objectively analyzed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a vehicle model performance boundary analysis method and device, equipment and a storage medium. BACKGROUND

[0002] In the field of automobile research and development, performance boundaries directly affect the energy efficiency and handling performance of vehicles. Determining and analyzing the performance boundaries (such as weight, energy consumption, frontal area and drag coefficient) of a vehicle model is a key link in vehicle design and market positioning.

[0003] In existing solutions, the determination process of performance boundaries relies on manual analysis or experience judgment. A large amount of experimental data and market research are often needed by researchers to evaluate the performance of new vehicle models and market positioning. The parameters of the target vehicle model and a small number of competitive vehicle models are compared one by one through manual methods. However, manual analysis is difficult to systematically process massive existing vehicle model data, the analysis range is limited, and experience judgment is highly subjective. There is a lack of unified and objective quantitative standards. Different teams or personnel may draw different conclusions, and the analysis process and results have poor repeatability. Therefore, how to efficiently and objectively analyze the performance boundaries of vehicle models has become a problem to be solved.

[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a vehicle model performance boundary analysis method, device, equipment and storage medium, which aims to solve the technical problem of how to efficiently and objectively analyze the performance boundaries of vehicle models.

[0006] To achieve the above-mentioned purpose, the present application provides a vehicle model performance boundary analysis method, which comprises the following steps: obtaining a performance boundary training data set; performing cluster analysis on the performance boundary training data set to obtain a to-be-matched performance cluster; matching the performance parameters of a to-be-analyzed vehicle model with the to-be-matched performance cluster to obtain a target performance cluster to which the to-be-analyzed vehicle model belongs; determining the performance boundaries of the to-be-analyzed vehicle model based on the target performance cluster In an embodiment, the step of performing cluster analysis on the performance boundary training data set to obtain a to-be-matched performance cluster comprises the following steps: extracting vehicle weight, energy consumption limit, frontal area and drag coefficient from the performance boundary training data set to obtain performance parameter data; constructing a multi-dimensional feature space based on the performance parameter data; grouping data points in the multi-dimensional feature space by cluster analysis to obtain a performance cluster to be matched.

[0007] In an embodiment, the step of constructing the multi-dimensional feature space based on the performance parameter data comprises: determining an aerodynamic characteristic parameter based on the windward area and the wind resistance coefficient; constructing a multi-dimensional feature space based on the vehicle weight, the energy consumption limit value, and the aerodynamic characteristic parameter.

[0008] In an embodiment, the step of grouping data points in the multi-dimensional feature space by cluster analysis to obtain a performance cluster to be matched comprises: initializing a preset number of center points by cluster analysis; determining a corresponding center point of each data point in the multi-dimensional feature space from the preset number of center points to obtain a center point assignment result; updating the positions of the preset number of center points based on the center point assignment result to obtain a performance cluster to be matched.

[0009] In an embodiment, the step of matching the performance parameter of the vehicle to be analyzed with the performance cluster to be matched to obtain a target performance cluster to which the vehicle to be analyzed belongs comprises: obtaining center point coordinates of the performance cluster to be matched; calculating a spatial distance between the performance parameter of the vehicle to be analyzed and the center point coordinates; matching the vehicle to be analyzed with the performance cluster to be matched based on the spatial distance to obtain a target performance cluster to which the vehicle to be analyzed belongs.

[0010] In an embodiment, the step of determining the performance boundary of the vehicle to be analyzed based on the target performance cluster comprises: extracting performance parameters of target vehicles from the target performance cluster to obtain a target performance extraction result; determining numerical ranges of vehicle weight, energy consumption limit value, and aerodynamic characteristic parameter respectively according to the target performance extraction result to obtain a performance boundary of the vehicle to be analyzed.

[0011] In an embodiment, after the step of determining the performance boundary of the vehicle to be analyzed based on the target performance cluster, the method further comprises: constructing a three-dimensional coordinate system based on vehicle weight, energy consumption limit value, and aerodynamic characteristic parameter; drawing corresponding data points of the performance boundary training data set, the vehicle to be analyzed, and the performance cluster center point in the three-dimensional coordinate system respectively to obtain a performance comparison visual interface; When a user click operation is detected on the performance comparison visualization interface, performance parameter information of a corresponding position data point is displayed in a preset format.

[0012] In addition, to achieve the above object, the present application also provides a vehicle model performance boundary analysis device, which comprises: a data acquisition module configured to acquire a performance boundary training data set; a data clustering module configured to perform clustering analysis on the performance boundary training data set to obtain a to-be-matched performance cluster; a performance matching module configured to match performance parameters of a to-be-analyzed vehicle model with the to-be-matched performance cluster to obtain a target performance cluster to which the to-be-analyzed vehicle model belongs; a boundary analysis module configured to determine a performance boundary of the to-be-analyzed vehicle model based on the target performance cluster.

[0013] In addition, to achieve the above object, the present application also provides a vehicle model performance boundary analysis device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the vehicle model performance boundary analysis method as described above.

[0014] In addition, to achieve the above object, the present application also provides a storage medium, which is a computer readable storage medium, and a computer program is stored on the storage medium, and the computer program is executed by a processor to implement the steps of the vehicle model performance boundary analysis method as described above.

[0015] In addition, to achieve the above object, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the vehicle model performance boundary analysis method as described above.

[0016] The one or more technical solutions provided by the present application have at least the following technical effects: The performance boundary training data set is acquired, and the scattered existing vehicle model data in the performance boundary training data set is converted into a structured to-be-matched performance cluster through clustering analysis, which replaces the traditional manual experience grouping of vehicle models, improves the objectivity and accuracy of grouping, matches the performance parameters of the to-be-analyzed vehicle model with the to-be-matched performance cluster to obtain a target performance cluster to which the to-be-analyzed vehicle model belongs, provides clear and quantitative performance boundary design reference for researchers through the target performance cluster, replaces the traditional manual estimation range, can efficiently and objectively analyze the vehicle model performance boundary, and helps to reduce the number of sample vehicle tests and reduce the research and development cost. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the application and, together with the description, further serve to explain the principles of the application.

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the accompanying drawings required by the embodiments or the prior art description will be briefly introduced as follows. Obviously, those skilled in the art can obtain other drawings from these drawings without any creative effort.

[0019] Figure 1 The flowchart provided for the first embodiment of the vehicle performance boundary analysis method of the present application; Figure 2 The flowchart provided for the second embodiment of the vehicle performance boundary analysis method of the present application; Figure 3 The three-dimensional scatter diagram of the performance comparison visualization interface provided for the second embodiment of the vehicle performance boundary analysis method of the present application; Figure 4 The click display diagram of the performance comparison visualization interface provided for the second embodiment of the vehicle performance boundary analysis method of the present application; Figure 5 The module structure diagram of the vehicle performance boundary analysis device of the embodiment of the present application; Figure 6 The device structure diagram of the hardware running environment involved in the vehicle performance boundary analysis method in the embodiment of the present application.

[0020] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0022] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings of the specification and the specific embodiments.

[0023] The main solution of the embodiment of the present application is: obtaining a performance boundary training data set; performing cluster analysis on the performance boundary training data set to obtain a to-be-matched performance cluster; matching the performance parameters of a to-be-analyzed vehicle model with the to-be-matched performance cluster to obtain a target performance cluster to which the to-be-analyzed vehicle model belongs; and determining the performance boundary of the to-be-analyzed vehicle model based on the target performance cluster. This solution can efficiently and objectively analyze the performance boundary of the vehicle model.

[0024] Since in the prior scheme, the performance boundary determination process relies on manual analysis or experience judgment, the R&D personnel often need a large amount of experimental data and market research to evaluate the performance of the new vehicle model and the market positioning, and compare the parameters of the target vehicle model with a small number of competitive vehicle models one by one through manual method. However, manual analysis is difficult to systematically process a large amount of existing vehicle data, the analysis range is limited, and the experience judgment is subjective, lacking unified and objective quantitative standards, different teams or personnel may draw different conclusions, and the analysis process and results are poor in repeatability. Therefore, how to efficiently and objectively analyze the vehicle performance boundary has become a problem to be solved.

[0025] The present application provides a solution, acquires a performance boundary training data set, and converts the scattered existing vehicle data in the performance boundary training data set into a structured performance cluster to be matched through clustering analysis, replaces the traditional manual experience grouping method of the vehicle, improves the objectivity and accuracy of the grouping, matches the performance parameters of the vehicle to be analyzed with the performance cluster to be matched to obtain the target performance cluster to which the vehicle to be analyzed belongs, and provides a clear and quantitative performance boundary design reference for the R&D personnel through the target performance cluster, replaces the traditional manual estimation method, can efficiently and objectively analyze the vehicle performance boundary, and helps to reduce the number of sample vehicle tests and reduce the R&D cost.

[0026] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a vehicle performance boundary analysis device, etc. capable of realizing the above functions. The vehicle performance boundary analysis device is taken as an example to describe the embodiment and the following embodiments.

[0027] Based on this, the embodiment of the present application provides a vehicle performance boundary analysis method, which refers to Figure 1 , Figure 1 The flowchart of the first embodiment of the vehicle performance boundary analysis method of the present application is shown.

[0028] In the embodiment, the vehicle performance boundary analysis method includes steps S10-S40: Step S10, acquiring a performance boundary training data set; It should be noted that the performance boundary training data set is a basic data set for subsequent clustering analysis, which records the names of existing vehicle models and corresponding performance parameter values.

[0029] It should be understood that before the performance boundary analysis of the vehicle to be analyzed, the existing vehicle data will be obtained from the preset storage carrier (such as an Excel file), which collectively constitutes the performance boundary training data set. After obtaining the existing vehicle data, the extracted data needs to be preprocessed to check the integrity and validity of the data. Specifically, it can be detected whether there is a performance parameter value missing and a performance parameter value abnormal (such as a negative vehicle weight value) in the performance boundary training data set. If there is a performance parameter value missing or a performance parameter value abnormal, the corresponding data needs to be supplemented or excluded to obtain the performance boundary training data set that can be used for subsequent clustering analysis.

[0030] Step S20, clustering analysis is performed on the performance boundary training data set to obtain a performance cluster to be matched; It should be noted that clustering analysis is a data mining technology, and the core purpose is to divide data sets with similar characteristics into multiple different groups (i.e. clusters), so that the similarity of data points in the same group is high, and the difference between data points in different groups is large. The performance cluster to be matched is each data group obtained after clustering analysis, representing a set of existing vehicles with similar performance characteristics. Each performance cluster to be matched not only contains the existing vehicle data belonging to it, but also contains the corresponding key performance reference indicators (such as energy consumption average) and center point coordinates, which are used for subsequent matching with the vehicle to be analyzed.

[0031] It should be understood that after obtaining the performance boundary training data set, the performance boundary training data set will be subjected to feature engineering processing to obtain multi-dimensional performance description features that are more in line with the actual engineering needs of automobile research and development. The multi-dimensional performance description features can be subjected to clustering analysis by the K-means clustering algorithm to obtain the performance cluster to be matched. The K-means clustering algorithm is a partition-based clustering algorithm, which is used to divide data points into K clusters, so that the similarity of data points in each cluster is high, while the similarity of data points between different clusters is low. The K-means clustering algorithm optimizes the clustering result by minimizing the sum of squared errors (SSE, Sum of Squared Errors) within the cluster, and through iterative optimization, the best cluster center point can be found, thereby realizing effective classification of data points.

[0032] In a feasible implementation, step S20 can include steps S21-S23: Step S21, vehicle weight, energy consumption limit, frontal area, and drag coefficient are extracted from the performance boundary training data set to obtain performance parameter data; It should be noted that vehicle weight refers to the curb weight of existing models (unit: kg), a key parameter characterizing vehicle structural design that directly affects energy consumption, handling performance, and safety performance. Energy consumption limits refer to vehicle energy consumption indicators, such as fuel consumption per 100 kilometers or electricity consumption per 100 kilometers, and are core indicators for measuring vehicle energy efficiency. Frontal area refers to the effective area of ​​the vehicle's frontal projection when in motion, usually measured in square meters, and is an important parameter affecting vehicle air resistance. A larger frontal area generally results in higher air resistance, thus increasing energy consumption. The drag coefficient, or Cd value, is a dimensionless parameter characterizing the degree to which the vehicle's shape affects airflow resistance. A smaller Cd value indicates a better aerodynamic design and lower air resistance.

[0033] In addition, the performance parameter data is a collection of four core parameters extracted from the performance boundary training dataset: weight, energy consumption limit, frontal area, and drag coefficient. Non-analysis fields such as vehicle model name have been removed, and only numerical parameters used for subsequent feature construction and clustering have been retained. It is necessary to ensure that all performance parameter data have a unified parameter format and consistent units, such as weight being uniformly expressed in kg and energy consumption limit being uniformly expressed in the same measurement standard.

[0034] It should be understood that numerical data used for performance analysis in the performance boundary training dataset can be read using data processing tools (such as MATLAB or a programming environment that supports Excel reading), and the four parameters of vehicle weight, energy consumption limit, frontal area and drag coefficient for each existing model can be extracted row by row to obtain performance parameter data.

[0035] Step S22: Construct a multi-dimensional feature space based on the performance parameter data; It should be noted that the multidimensional feature space is an abstract mathematical space used to describe vehicle performance. Its dimensions are determined by the core feature parameters that affect the performance boundary. Each dimension corresponds to a key performance indicator, and each point in the space represents the performance state of a vehicle. Specifically, the multidimensional feature space in this embodiment can be a four-dimensional feature space or a three-dimensional feature space.

[0036] It should be understood that after obtaining the performance parameter data, a four-dimensional feature space can be directly constructed based on vehicle weight, energy consumption limit, frontal area, and drag coefficient. Alternatively, a new feature can be established based on two of the vehicle weight, energy consumption limit, frontal area, and drag coefficient, and then combined with the other two to construct a three-dimensional feature space.

[0037] In one feasible implementation, step S22 may include: The aerodynamic characteristic parameters are determined based on the frontal area and the drag coefficient. A multidimensional feature space is constructed based on the vehicle weight, the energy consumption limit, and the aerodynamic characteristic parameters.

[0038] It should be noted that aerodynamic characteristic parameters are single parameters that comprehensively reflect the aerodynamic performance of a vehicle. They can be calculated by multiplying the frontal area and the drag coefficient, i.e., aerodynamic characteristic parameter = frontal area × drag coefficient. This parameter integrates two originally independent aerodynamic indicators (frontal area and drag coefficient) into one dimension, directly relating to the magnitude of air resistance when the vehicle is in motion. The greater the air resistance, the higher the energy consumption. This retains its engineering significance while reducing the dimensionality of the feature space, simplifying subsequent clustering calculations.

[0039] It should be understood that after obtaining the performance parameter data of existing vehicle models, the frontal area and drag coefficient of each model are extracted. Aerodynamic characteristic parameters are then calculated by multiplying the frontal area and drag coefficient. These aerodynamic characteristic parameters are then correlated with the original vehicle weight and energy consumption limits, forming three sets of parameters: "vehicle weight - energy consumption limit - aerodynamic characteristic parameters." A three-dimensional mathematical space is constructed using vehicle weight as the first dimension (characterizing vehicle structural design), energy consumption limit as the second dimension (characterizing energy efficiency), and aerodynamic characteristic parameters as the third dimension (characterizing aerodynamic performance). Each performance parameter data point is used as the coordinates of a point in this space, and the coordinates of all performance parameter data points in the performance boundary training dataset are mapped onto this three-dimensional space, completing the construction of the multi-dimensional feature space.

[0040] In this embodiment, by constructing a multi-dimensional feature space, the originally scattered performance parameters are transformed into intuitive spatial coordinates, which facilitates the subsequent identification of vehicle groups with similar performance through clustering algorithms. By introducing aerodynamic feature parameters to integrate key aerodynamic indicators and constructing a three-dimensional feature space, it can align with the core focus dimensions of structure, energy consumption, and aerodynamics in automotive R&D, making the subsequent clustering results more valuable.

[0041] Step S23: Group the data points in the multidimensional feature space through cluster analysis to obtain the performance clusters to be matched.

[0042] It should be understood that in the process of cluster analysis, the K-means clustering algorithm can be used to group data points in the multidimensional feature space, and similar data points (i.e., models with similar performance) in the multidimensional feature space are grouped into the same group (i.e., clusters), so that the similarity of data points within the same group is high and the similarity of data points between different groups is low, thus obtaining the performance clusters to be matched.

[0043] In one feasible implementation, step S23 may include: A preset number of centroids are initialized using cluster analysis; The center point of each data point in the multidimensional feature space is determined from the preset number of center points to obtain the center point allocation result. The positions of the preset number of center points are updated based on the center point allocation results to obtain the performance clusters to be matched.

[0044] It should be noted that the preset number of centroids are the initial cluster centers set by the K-means clustering algorithm used in the cluster analysis. The number is consistent with the preset number of clusters K. Each centroid is a coordinate point in the multidimensional feature space, representing the center position of a certain hypothesized performance cluster in the initial analysis. The initialization of centroids must be based on a random seed to ensure that the position can be reproduced each time.

[0045] In addition, the center point assignment result refers to the result of assigning each data point in the multidimensional feature space to the nearest center point. The assignment can be based on the Euclidean distance between the data point and the center point. The Euclidean distance is the straight-line distance between two points in three-dimensional space. The smaller the distance, the more similar the performance represented by the data point and the center point is.

[0046] It should be understood that the K-means clustering algorithm allows setting a preset number of clusters K (e.g., K=10) and a random seed (e.g., random seed 100). Based on the random seed, a preset number of center points are randomly generated in the multidimensional feature space as initial center points, and the coordinates of all initial center points are recorded. The Euclidean distance between each data point in the multidimensional feature space and the K initial center points is calculated, and the nearest center point is determined as the corresponding center point for each data point, resulting in the center point allocation result. After obtaining the center point allocation result, for all data points in a performance cluster in the center point allocation result, the average value of all performance parameters (vehicle weight, energy consumption limit, and aerodynamic characteristic parameters) is calculated. Based on these average values, new cluster centers are obtained, and the positions of the preset number of center points are updated. The process of determining the corresponding center point for each data point in the multidimensional feature space from the preset number of center points is repeated until the change in the coordinates of the center point of each performance cluster is less than a preset threshold in two consecutive iterations, indicating that the algorithm has converged. After the algorithm converges, the vehicle group corresponding to each center point becomes a performance cluster to be matched. At the same time, the average energy consumption of all vehicles in each cluster is calculated as the performance reference index of the cluster. Finally, a preset number of performance clusters to be matched are obtained, each containing a list of data points, cluster number, coordinates of cluster center point, and average energy consumption.

[0047] Step S30: Match the performance parameters of the vehicle model to be analyzed with the performance cluster to be matched to obtain the target performance cluster to which the vehicle model to be analyzed belongs; It should be noted that the vehicle model to be analyzed refers to the vehicle whose performance boundaries and market positioning need to be determined. Performance parameters of multiple vehicle models can be stored in the vehicle model analysis dataset. These performance parameters are the core data for the vehicle whose performance boundaries need to be determined. The parameter categories are completely consistent with the performance boundary training dataset, including vehicle name, vehicle weight, energy consumption limit, frontal area, and drag coefficient. These parameters are the core basis for matching the vehicle model to the performance cluster to be matched, and the format and units must be consistent with the performance boundary training dataset. Automated checks can avoid file conflicts and improve system robustness. The target performance cluster is the performance cluster to be matched that has the highest performance similarity to the vehicle model itself.

[0048] For example, Table 1 shows a partial sample of data from a performance boundary training dataset, and Table 2 shows a partial sample of data from a vehicle model dataset to be analyzed. The format and units of the vehicle model dataset to be analyzed are consistent with those of the performance boundary training dataset. The vehicle model dataset to be analyzed and the performance boundary training dataset can be stored in Sheet1 and Sheet2 of an Excel file, respectively.

[0049] Table 1

[0050] Continued from Table 1

[0051] Table 2

[0052] It should be understood that the K nearest neighbors search algorithm can be used to find the K nearest neighbors of each vehicle model to be analyzed in the multidimensional feature space, so as to predict the performance cluster to which the data points corresponding to the performance parameters of the vehicle model to be analyzed belong. The performance parameters of the vehicle model to be analyzed are matched with the performance clusters to be matched to obtain the target performance cluster to which the vehicle model to be analyzed belongs.

[0053] In one feasible implementation, step S30 may include: Obtain the coordinates of the center point of the performance cluster to be matched; Calculate the spatial distance between the performance parameters of the vehicle model to be analyzed and the coordinates of the center point; Based on the spatial distance, the vehicle model to be analyzed is matched with the performance cluster to be matched, thereby obtaining the target performance cluster to which the vehicle model to be analyzed belongs.

[0054] It should be noted that the coordinates of the center point of the performance cluster to be matched are the core location parameters of each cluster obtained through cluster analysis. The coordinate dimension corresponds to a three-dimensional feature space (weight, energy consumption limit, aerodynamic characteristic parameters), representing the average performance level of all existing models within that cluster. The spatial distance is the Euclidean distance between the performance parameters of the model to be analyzed and the coordinates of the center point of each performance cluster in the three-dimensional feature space, used to measure the similarity between the model to be analyzed and the average performance of each cluster.

[0055] It should be understood that after obtaining a preset number of performance clusters to be matched, the coordinates of the center point of each cluster are extracted one by one to ensure that the coordinate dimension is consistent with the three-dimensional feature space (vehicle weight, energy consumption limit, aerodynamic characteristic parameters). The performance parameters of the vehicle to be analyzed are preprocessed by calculating the aerodynamic characteristic parameters through the product of the frontal area and the drag coefficient, ensuring that the parameter dimension is consistent with the center point coordinates. This yields the three-dimensional parameters: vehicle weight, energy consumption limit, and aerodynamic characteristic parameters. These three-dimensional parameters and the center point coordinates of the preset number of performance clusters to be matched are substituted into the Euclidean distance formula to calculate a preset number of spatial distance values. These spatial distance values ​​are then sorted by size, and the value with the smallest distance is selected. The performance cluster containing the center point of this value is the target performance cluster. If the distance value is far beyond the normal range (e.g., greater than 100) due to abnormal parameters of the vehicle to be analyzed (e.g., a negative vehicle weight), it indicates that no corresponding point was found, prompting a check of parameter validity to ensure reliable matching results.

[0056] Step S40: Determine the performance boundary of the vehicle model to be analyzed based on the target performance cluster.

[0057] It should be noted that the performance boundary is the reasonable design range of the vehicle model under analysis in terms of performance parameters. It is determined based on the parameter distribution of all existing vehicles within the target performance cluster and can reflect the market competitive performance range and design optimization direction of the vehicle model under analysis.

[0058] It should be understood that, from all existing vehicle data included in the target performance cluster, the maximum and minimum values ​​of each category of performance parameters can be statistically analyzed to determine the range of each performance parameter. The boundary can then be refined by combining the average energy consumption of the target performance cluster to obtain the performance boundary of the vehicle to be analyzed.

[0059] In one possible implementation, step S40 may include: The performance parameters of the target vehicle model are extracted from the target performance cluster to obtain the target performance extraction results; Based on the target performance extraction results, the numerical ranges of vehicle weight, energy consumption limits, and aerodynamic characteristic parameters are determined to obtain the performance boundaries of the vehicle model to be analyzed.

[0060] It should be noted that the target vehicle models are all existing vehicle models included in the target performance cluster. These models have the highest performance similarity to the vehicle model to be analyzed and are the core reference objects for determining the performance boundary. Their data comes from the performance boundary training dataset. The target performance extraction result is a set of core performance parameters extracted from all target vehicle models in the target performance cluster. The parameter categories are consistent with the three-dimensional feature space (vehicle weight, energy consumption limit, aerodynamic characteristic parameters). It is necessary to ensure that the parameters are complete, without omissions, and correspond one-to-one with the target vehicle models. The numerical range is a reasonable interval formed by statistically analyzing the maximum and minimum values ​​of each parameter in the target performance extraction result for weight, energy consumption limit, and aerodynamic characteristic parameters, reflecting the performance distribution range of existing vehicle models within the target cluster.

[0061] It should be understood that after determining the target performance cluster of the vehicle model to be analyzed, the performance parameters of all existing vehicles within the target performance cluster, i.e., the target vehicle models, can be extracted. For the three performance parameters extracted from the target performance results—vehicle weight, energy consumption limit, and aerodynamic characteristic parameters—the maximum and minimum values ​​are calculated respectively to obtain the numerical ranges for vehicle weight, energy consumption limit, and aerodynamic characteristic parameters (e.g., weight 1800-2000kg, energy consumption 5.0-5.5, area × Cd 2.3-2.7). These three numerical ranges are then adjusted according to design requirements. For example, by combining the average energy consumption of the target cluster, the median value of the energy consumption limit range is adjusted to be close to the average energy consumption, thus obtaining the performance boundary of the vehicle model to be analyzed.

[0062] This embodiment provides a method for vehicle performance boundary analysis. It obtains a performance boundary training dataset and uses cluster analysis to transform the scattered existing vehicle data in the training dataset into structured performance clusters to be matched. This replaces the traditional method of manually grouping vehicles based on experience, improving the objectivity and accuracy of grouping. The performance parameters of the vehicle to be analyzed are matched with the performance clusters to obtain the target performance cluster to which the vehicle belongs. These target performance clusters provide R&D personnel with a clear and quantitative reference for performance boundary design, replacing the traditional method of manually estimating the range. This allows for efficient and objective analysis of vehicle performance boundaries, helping to reduce the number of prototype tests and lower R&D costs.

[0063] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 After step S40, the vehicle performance boundary analysis method further includes steps S50 to S70: Step S50: Construct a three-dimensional coordinate system based on vehicle weight, energy consumption limits, and aerodynamic characteristic parameters; It should be noted that the three-dimensional coordinate system is a spatial mathematical model used to intuitively display the relationship between vehicle performance parameters. It contains three mutually perpendicular coordinate axes, each corresponding to a core performance indicator. It can transform the originally abstract parameter data into visualized spatial points, making it easier for R&D personnel to quickly compare the performance differences of different vehicle models.

[0064] It should be understood that a three-dimensional coordinate system can be constructed by using aerodynamic characteristic parameters (frontal area × Cd) as the X-axis, vehicle weight as the Y-axis, and energy consumption limit as the Z-axis, and constructing a coordinate system framework through data processing and visualization tools (such as MATLAB).

[0065] Step S60: Based on the performance boundary training dataset, the vehicle model to be analyzed, and the center point of the performance cluster, draw the corresponding data points in the three-dimensional coordinate system to obtain a performance comparison visualization interface. It should be noted that the data points corresponding to the performance boundary training dataset are the spatial location representations of each existing vehicle performance parameter data in the three-dimensional coordinate system. The data points corresponding to the vehicle to be analyzed are the spatial location representations of the vehicle to be analyzed in the three-dimensional coordinate system. The data points corresponding to the center points of performance clusters are the average performance location representations of each performance cluster to be matched in the three-dimensional coordinate system.

[0066] Additionally, the performance comparison visualization interface is a 3D visualization chart that integrates the performance boundary training dataset, the vehicle model to be analyzed, and the performance cluster data. It includes a 3D coordinate system, all data points, and a legend, which can intuitively show the performance positional relationship between the vehicle model to be analyzed and existing models, as well as the cluster center point. The legend is placed outside the interface and labels each cluster number and the average energy consumption.

[0067] It should be understood that when plotting the performance boundary training dataset, the vehicle model to be analyzed, and the data points corresponding to the performance cluster center points in a three-dimensional coordinate system, different graphical elements can be used to represent the data points corresponding to the performance boundary training dataset, the data points corresponding to the vehicle model to be analyzed, and the data points corresponding to the performance cluster center points, respectively. By comparing the vehicle model to be analyzed with other models within the cluster using the three-dimensional graph, its market positioning (such as economy or luxury) and potential competitors can be identified. For example, if the analyzed vehicle falls into the low-energy consumption cluster, its design can be optimized to further reduce energy consumption.

[0068] For example, refer to Figure 3 , Figure 3 This is a three-dimensional scatter plot of the performance comparison visualization interface provided in Embodiment 2 of the vehicle performance boundary analysis method of this application. Figure 3As shown, there are 12 performance clusters to be matched. The X-axis represents the frontal area × Cd, used to characterize aerodynamic characteristics; the Y-axis represents the vehicle weight (unit: kg), used to reflect structural design; and the Z-axis represents the energy consumption limit, used to measure energy efficiency. Sheet1 is the performance boundary training dataset. Clusters 1 to 12 in Sheet1 represent the data points corresponding to the vehicle models to be analyzed, using solid circles as graphic elements. Different colors are used for the solid circles of different performance clusters, and black borders are added to enhance the distinction between clusters, ensuring that R&D personnel can quickly identify the vehicle distribution of different clusters. Center points 1 to 12 represent the data points corresponding to the center points of performance clusters, using X-shapes as graphic elements. The color is consistent with the color of the corresponding performance cluster, highlighting the average performance level of each cluster, facilitating comparison of the difference between the average performance of the vehicle model to be analyzed and the average performance of the cluster. Data1 to data12 represent the data points corresponding to the vehicle models to be analyzed, using hollow squares as graphic elements. The color is consistent with the color of the target performance cluster to which the vehicle model to be analyzed belongs, and the vehicle name and cluster number are labeled next to the square, facilitating quick location of the vehicle model to be analyzed and its affiliation. The background of the performance comparison visualization interface is set to white, and the axis labels are clearly visible.

[0069] Step S70: When a user click operation is detected on the performance comparison visualization interface, the performance parameter information of the corresponding data point is displayed in a preset format.

[0070] It should be noted that the user click operation refers to the interactive behavior of R&D personnel clicking a data point with the left mouse button on the performance comparison visualization interface. The purpose is to obtain detailed performance parameters of the corresponding vehicle model or cluster. The preset format is a fixed text format for displaying performance parameter information. The performance parameter information of the corresponding data point is the detailed performance data associated with the data point clicked by the user, and the content of the information varies depending on the type of data point.

[0071] It should be understood that the interactive function of the visualization tool monitors the user's mouse click position on the performance comparison visualization interface in real time and records the three-dimensional coordinates of the click position. The recorded click coordinates are compared with the three-dimensional coordinates of all data points on the interface, and the difference between the click coordinates and the coordinates of each data point is calculated. If the difference between the coordinates of a data point and the click coordinates is less than a small tolerance (such as 1e-6), then the data point is determined to be the target data point clicked by the user; if the difference between the coordinates of all data points and the click coordinates is greater than 1e-6, then the data point is determined to be missing, and the message "No corresponding point found" is displayed. Based on the data source of the target data point (such as the performance boundary training dataset, the vehicle model to be analyzed, and the cluster center point), detailed parameters are extracted from the corresponding dataset (such as Sheet1 storing the performance boundary training dataset, Sheet2 storing the vehicle model to be analyzed, and the clustering results of the cluster center points are saved), organized into text according to a preset format, and displayed in a designated area of ​​the performance comparison visualization interface (such as the information box in the upper right corner).

[0072] For example, refer to Figure 4 , Figure 4 This is a schematic diagram showing the performance comparison visualization interface clicked in Embodiment 2 of the vehicle performance boundary analysis method of this application. The target data point clicked by the user is detected to be the data point corresponding to existing vehicle model 8 and existing vehicle model 11 in the performance boundary training dataset. The datasets, vehicle names, frontal area × Cd, vehicle weight, and energy consumption limits of existing vehicle model 8 and existing vehicle model 11 are read and displayed in the upper right corner information box of the corresponding data point in the performance comparison visualization interface.

[0073] This embodiment provides a vehicle performance boundary analysis method. A three-dimensional coordinate system is constructed based on vehicle weight, energy consumption limits, and aerodynamic characteristic parameters. Data points are plotted in the three-dimensional coordinate system based on the performance boundary training dataset, the vehicle model to be analyzed, and the center points of performance clusters, resulting in a performance comparison visualization interface. This interface can intuitively display the performance comparison between the analyzed vehicle model and existing models. When a user click is detected on the performance comparison visualization interface, the performance parameter information of the corresponding data point is displayed in a preset format. An interactive click query function is integrated into the performance comparison visualization interface, allowing users to directly obtain detailed parameters for any vehicle model, reducing data verification time.

[0074] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the vehicle performance boundary analysis method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0075] This application also provides a vehicle performance boundary analysis device, please refer to... Figure 5 The vehicle performance boundary analysis device includes: Data acquisition module 10 is used to acquire the performance boundary training dataset; Data clustering module 20 is used to perform cluster analysis on the performance boundary training dataset to obtain the performance clusters to be matched; The performance matching module 30 is used to match the performance parameters of the vehicle model to be analyzed with the performance cluster to be matched, so as to obtain the target performance cluster to which the vehicle model to be analyzed belongs; Boundary analysis module 40 is used to determine the performance boundary of the vehicle model to be analyzed based on the target performance cluster.

[0076] In one embodiment, the data clustering module 20 is further configured to extract vehicle weight, energy consumption limit, frontal area, and drag coefficient from the performance boundary training dataset to obtain performance parameter data; construct a multidimensional feature space based on the performance parameter data; and group the data points in the multidimensional feature space through cluster analysis to obtain performance clusters to be matched.

[0077] In one embodiment, the data clustering module 20 is further configured to determine aerodynamic characteristic parameters based on the frontal area and the drag coefficient; and to construct a multidimensional feature space based on the vehicle weight, the energy consumption limit, and the aerodynamic characteristic parameters.

[0078] In one embodiment, the data clustering module 20 is further configured to initialize a preset number of centroids through clustering analysis; determine the corresponding centroid of each data point in the multidimensional feature space from the preset number of centroids to obtain a centroid allocation result; and update the position of the preset number of centroids based on the centroid allocation result to obtain a performance cluster to be matched.

[0079] In one embodiment, the performance matching module 30 is further configured to obtain the center point coordinates of the performance cluster to be matched; calculate the spatial distance between the performance parameters of the vehicle to be analyzed and the center point coordinates; and match the vehicle to be analyzed with the performance cluster to be matched based on the spatial distance to obtain the target performance cluster to which the vehicle to be analyzed belongs.

[0080] In one embodiment, the boundary analysis module 40 is further configured to extract the performance parameters of the target vehicle model from the target performance cluster to obtain the target performance extraction result; and to determine the numerical range of vehicle weight, energy consumption limit and aerodynamic characteristic parameters based on the target performance extraction result to obtain the performance boundary of the vehicle model to be analyzed.

[0081] In one embodiment, the boundary analysis module 40 is further configured to construct a three-dimensional coordinate system based on vehicle weight, energy consumption limits, and aerodynamic characteristic parameters; draw corresponding data points in the three-dimensional coordinate system based on the performance boundary training dataset, the vehicle model to be analyzed, and the center point of the performance cluster, to obtain a performance comparison visualization interface; when a user click operation is detected on the performance comparison visualization interface, the performance parameter information of the corresponding data point is displayed in a preset format.

[0082] The vehicle performance boundary analysis device provided in this application, employing the vehicle performance boundary analysis method in the above embodiments, can solve the technical problem of how to efficiently and objectively analyze vehicle performance boundaries. Compared with the prior art, the beneficial effects of the vehicle performance boundary analysis device provided in this application are the same as those of the vehicle performance boundary analysis method provided in the above embodiments, and other technical features in the vehicle performance boundary analysis device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0083] This application provides a vehicle performance boundary analysis device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the vehicle performance boundary analysis method in the above embodiment 1.

[0084] The following is for reference. Figure 6 The diagram illustrates a structural schematic of a vehicle performance boundary analysis device suitable for implementing embodiments of this application. The vehicle performance boundary analysis device in this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The vehicle performance boundary analysis device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0085] like Figure 6As shown, the vehicle performance boundary analysis device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the vehicle performance boundary analysis device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touch screens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication device 1009 allows the vehicle performance boundary analysis device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows vehicle performance boundary analysis devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0086] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a 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, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0087] The vehicle performance boundary analysis device provided in this application, employing the vehicle performance boundary analysis method described in the above embodiments, can solve the technical problem of how to efficiently and objectively analyze vehicle performance boundaries. Compared with the prior art, the beneficial effects of the vehicle performance boundary analysis device provided in this application are the same as those of the vehicle performance boundary analysis method provided in the above embodiments, and other technical features of this vehicle performance boundary analysis device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0088] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0089] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0090] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the vehicle performance boundary analysis method in the above embodiments.

[0091] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory), or flash memory, optical fiber, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0092] The aforementioned computer-readable storage medium may be included in the vehicle performance boundary analysis device; or it may exist independently and not be installed in the vehicle performance boundary analysis device.

[0093] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the vehicle performance boundary analysis device, the device performs the following: acquires a performance boundary training dataset; performs cluster analysis on the training dataset to obtain performance clusters to be matched; matches the performance parameters of the vehicle to be analyzed with the performance clusters to be matched to obtain the target performance cluster to which the vehicle to be analyzed belongs; and determines the performance boundary of the vehicle to be analyzed based on the target performance cluster. This solution can efficiently and objectively analyze vehicle performance boundaries.

[0094] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0095] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0096] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0097] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described vehicle performance boundary analysis method, thereby solving the technical problem of how to efficiently and objectively analyze vehicle performance boundaries. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the vehicle performance boundary analysis method provided in the above embodiments, and will not be repeated here.

[0098] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle performance boundary analysis method described above.

[0099] The computer program product provided in this application can solve the technical problem of how to efficiently and objectively analyze the performance boundaries of vehicle models. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the vehicle model performance boundary analysis method provided in the above embodiments, and will not be repeated here.

[0100] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for boundary value analysis of vehicle performance, characterized in that, The vehicle performance boundary analysis method includes: Obtain the performance boundary training dataset; Cluster analysis is performed on the performance boundary training dataset to obtain the performance clusters to be matched; The performance parameters of the vehicle model to be analyzed are matched with the performance cluster to be matched to obtain the target performance cluster to which the vehicle model to be analyzed belongs; The performance boundaries of the vehicle model to be analyzed are determined based on the target performance cluster.

2. The method as described in claim 1, characterized in that, The step of performing cluster analysis on the performance boundary training dataset to obtain the performance clusters to be matched includes: Vehicle weight, energy consumption limit, frontal area, and drag coefficient are extracted from the performance boundary training dataset to obtain performance parameter data. A multidimensional feature space is constructed based on the performance parameter data; Cluster analysis is used to group data points in the multidimensional feature space to obtain performance clusters to be matched.

3. The method as described in claim 2, characterized in that, The step of constructing a multidimensional feature space based on the performance parameter data includes: The aerodynamic characteristic parameters are determined based on the frontal area and the drag coefficient. A multidimensional feature space is constructed based on the vehicle weight, the energy consumption limit, and the aerodynamic characteristic parameters.

4. The method as described in claim 2, characterized in that, The step of grouping data points in the multidimensional feature space through cluster analysis to obtain performance clusters to be matched includes: A preset number of centroids are initialized using cluster analysis; The center point of each data point in the multidimensional feature space is determined from the preset number of center points to obtain the center point allocation result. The positions of the preset number of center points are updated based on the center point allocation results to obtain the performance clusters to be matched.

5. The method as described in claim 1, characterized in that, The step of matching the performance parameters of the vehicle model to be analyzed with the target performance cluster to obtain the target performance cluster to which the vehicle model to be analyzed belongs includes: Obtain the coordinates of the center point of the performance cluster to be matched; Calculate the spatial distance between the performance parameters of the vehicle model to be analyzed and the coordinates of the center point; Based on the spatial distance, the vehicle model to be analyzed is matched with the performance cluster to be matched, thereby obtaining the target performance cluster to which the vehicle model to be analyzed belongs.

6. The method as described in claim 1, characterized in that, The step of determining the performance boundary of the vehicle model to be analyzed based on the target performance cluster includes: The performance parameters of the target vehicle model are extracted from the target performance cluster to obtain the target performance extraction results; Based on the target performance extraction results, the numerical ranges of vehicle weight, energy consumption limits, and aerodynamic characteristic parameters are determined to obtain the performance boundaries of the vehicle model to be analyzed.

7. The method according to any one of claims 1 to 6, characterized in that, After the step of determining the performance boundary of the vehicle model to be analyzed based on the target performance cluster, the method further includes: A three-dimensional coordinate system is constructed based on vehicle weight, energy consumption limits, and aerodynamic characteristic parameters; Based on the performance boundary training dataset, the vehicle model to be analyzed, and the center point of the performance cluster, the corresponding data points are plotted in the three-dimensional coordinate system to obtain a performance comparison visualization interface. When a user click is detected on the performance comparison visualization interface, the performance parameter information of the corresponding data point is displayed in a preset format.

8. A vehicle performance boundary analysis device, characterized in that, The device includes: The data acquisition module is used to acquire the performance boundary training dataset; The data clustering module is used to perform cluster analysis on the performance boundary training dataset to obtain the performance clusters to be matched; The performance matching module is used to match the performance parameters of the vehicle model to be analyzed with the performance cluster to be matched, so as to obtain the target performance cluster to which the vehicle model to be analyzed belongs; The boundary analysis module is used to determine the performance boundary of the vehicle model to be analyzed based on the target performance cluster.

9. A vehicle performance boundary analysis device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle performance boundary analysis method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the vehicle performance boundary analysis method as described in any one of claims 1 to 7.

Images