A big data user-side automobile spraying effect simulation system and method
Through the big data user-side automotive spraying effect simulation system, the machine learning model is used to predict the spray trajectory and effect, the problems of paint uniformity and gloss during the spraying process are solved, and the spraying effect is optimized and improved.
Patent Information
- Application Number
- CN202411028241.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-07-30
AI Technical Summary
The prior art is difficult to accurately analyze and calculate the appropriate spray gun angle, distance, movement speed and paint discharge speed based on the characteristics of the paint and the concave and convex conditions of the surface of the sprayed object, resulting in uneven spraying effect.
The big data user-side automotive spraying effect simulation system is adopted, including spraying module, spraying control module, spraying surface data acquisition module, spraying monitoring module, track generation module and spraying effect prediction module. The machine learning model predicts spraying trajectory and effect to achieve Real-time monitoring and visualization of spray data ensures even coating.
By monitoring and predicting spray data in real time, the spraying process is optimized, and the uniformity and gloss of the coating are improved, ensuring the final effect is met.
Smart Images

Figure CN118551674B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of automobile spraying, and in particular to a big data user-side automobile spraying use effect simulation system and method. Background Art
[0002] Spraying is a coating method that uses a spray gun or a disc atomizer to disperse the spray into uniform and fine droplets by pressure or centrifugal force and apply it to the surface of the object. It can be divided into air spray, airless spray, electrostatic spray and various derivative methods of the above basic spray forms, such as high-flow low-pressure atomization spray, thermal spray, automatic spray, multi-group spray, etc.
[0003] The prior art with publication number CN116078594A discloses a spraying system and a spraying method for obtaining a spraying positioning shape, and relates to the technical field of spraying systems. The spraying system for obtaining a spraying positioning shape comprises a clamping module, the transmitting end of the clamping module is connected to the receiving end of the center positioning module, the transmitting end of the center positioning module is connected to the receiving end of the correction module, and the transmitting end of the correction module is connected to the receiving end of the scanning module. By generating a data set for the original product based on the scanning data of the original product, and generating a 3D simulation model corresponding to the original product based on the data set of the original product, the position shape information of the product to be sprayed can be obtained quickly and accurately, and the sprayed product can be truly restored 1:1, thereby generating a spraying plan for the product, and the on-site staff can also manually correct the spraying data of the spraying plan to achieve accurate spraying operations on the sprayed product.
[0004] During spraying, the angle, distance, moving speed of the spray gun, the discharge speed of the paint and the surface unevenness of the sprayed object will all affect the spraying effect. How to analyze and calculate the appropriate spray gun angle, distance, moving speed and discharge speed of the paint according to the characteristics of the paint and the surface unevenness of the sprayed object to ensure that the paint is sprayed evenly on the surface of the sprayed object is a problem that urgently needs to be solved in the existing technology. Summary of the invention
[0005] The purpose of the present invention is to provide a big data user-side automobile spraying use effect simulation system and method to solve the above-mentioned deficiencies in the prior art.
[0006] In order to achieve the above-mentioned purpose, the present invention provides the following technical solutions: a big data user-side automobile spraying use effect simulation system, including a spraying module, a spraying control module, a spraying surface data acquisition module, a spraying monitoring module, a trajectory generation module, a spraying effect prediction module, and a spraying effect visualization module;
[0007] The spraying module is used to spray the paint onto the spraying surface of the car, wherein the spraying module can adopt an air spray gun, a high-pressure airless spray gun, an air-assisted spray gun, a portable electrostatic spray gun, etc.;
[0008] The spray control module is used to control the spray distance, spray angle, spray discharge speed, and spray movement direction of the spray module; the spray module can be controlled by setting electric slide rails, motors and other devices, and editing the PLC program;
[0009] The spray surface data acquisition module is used to obtain the surface shape data of the automobile to be sprayed, obtain the spray surface data, and generate a three-dimensional model of the spray surface based on the spray surface data;
[0010] The spray surface data acquisition module is also used to obtain the effect image data of the spray pattern sprayed by the spray module on the spray surface, and associate the effect image data with the corresponding spray surface data, wherein the effect image data includes the shape, size, and color depth of each position of the spray pattern, wherein the color depth of each position is used to judge the uniformity of spraying and the thickness of the paint at each position of the spray pattern, and the association relationship between the data can be established through the SQL tool;
[0011] The spray monitoring module is used to monitor the spray position, moving speed, spray angle, and spray discharge speed of the spray module, obtain spray data, and associate the spray data with the corresponding effect image data. The spray monitoring module can be composed of multiple sensors, and sensors with corresponding functions can be selected and set according to monitoring needs to realize the monitoring of the spray position, moving speed, spray angle, and spray discharge speed. The spray discharge speed is obtained by monitoring the amount of paint sprayed per unit time;
[0012] The trajectory generation module is used to train a first machine learning model based on spraying data and spraying surface data to obtain a trajectory prediction model, which is used to obtain a predicted spraying trajectory based on the input spraying surface data, and the spraying trajectory is a spraying data set composed of spraying data changing over time; wherein, the present invention does not limit the specific machine learning model, and can be selected according to actual needs during training, such as regression model, support vector machine model, random forest model, convolutional neural network, etc., and multiple models can be selected at the same time for combined use and training.
[0013] The spraying effect prediction module is used to train a second machine learning model based on the spraying data, the spraying surface data, and the effect image data to obtain a spraying effect prediction model, which is used to output predicted effect image data based on the input spraying data and the spraying surface data; because in the actual automobile painting spraying operation, it is usually necessary to spray a layer of primer first, and then spray the paint. The paint may need to be sprayed multiple times to ensure sufficient coverage of the paint and uniform color, and finally spray multiple layers of clear varnish to ensure sufficient protection of the coating and to ensure the glossiness of the coating. At this time, the spraying effect prediction model can be used to predict the spraying effect after each spraying, that is, the effect image data, to check whether the glossiness of the sprayed coating meets the requirements.
[0014] The spraying effect visualization module is used to visualize the predicted effect image data on the three-dimensional model of the spraying surface.
[0015] Furthermore, the spray surface data acquisition module is also used to save the spray surface data and the spray surface three-dimensional model, and associate the spray surface data and its corresponding spray surface three-dimensional model with the corresponding position of the vehicle of the corresponding vehicle model.
[0016] Furthermore, the surface shape data of the automobile to be sprayed can be obtained by scanning or data importing, and the spray surface data acquisition module for scanning the spray surface obtains the spray surface data by scanning and detecting, which specifically includes the following steps:
[0017] Taking images of the vehicle and the position of the vehicle that needs to be sprayed to obtain a vehicle image;
[0018] Based on the image recognition algorithm, the vehicle image is analyzed to identify the vehicle model and the location that needs to be sprayed;
[0019] Detect whether the spray surface data acquisition module stores the spray surface data and the spray surface three-dimensional model of the corresponding position of the vehicle of the corresponding vehicle model;
[0020] If yes, the corresponding spray surface data and the spray surface three-dimensional model are exported, and the spray surface data are exported and input into the trajectory generation module and the spray effect prediction module, and used as the input of the trajectory prediction model and the spray effect prediction model respectively;
[0021] If not, scan the surface of the car that needs to be sprayed to obtain the sprayed surface data and the corresponding sprayed surface three-dimensional model. The sprayed surface data can be obtained by scanning the car surface through laser scanning, depth camera, etc., and the corresponding sprayed surface three-dimensional model is generated.
[0022] Furthermore, the trajectory generation module trains the first machine learning model, specifically comprising the following steps:
[0023] Obtaining an effect image corresponding to the effect image data;
[0024] Screening effect images that meet the standards from the effect images, and acquiring corresponding effect image data to obtain effect image training data;
[0025] Retrieving the spray surface data associated with the effect image training data to obtain the spray surface training data, and retrieving the spraying data associated with the spray surface training data to obtain the spraying training data;
[0026] Based on the spraying training data and the spraying surface training data, a first machine learning model is trained to obtain a trajectory prediction model. How to use data to train the model is common knowledge in the prior art and is directly applied without any changes. Therefore, it is not described in detail in this technical solution, and it will not cause trouble to this technical solution based on the field. When the accuracy of the trained machine learning model reaches the set threshold, the parameters of the machine learning model at this time are determined to obtain the corresponding trajectory prediction model or spraying effect prediction model.
[0027] Furthermore, the effect image data collected by the spray surface data collection module also includes glossiness data of the spray pattern, and the glossiness of the spray surface after spraying, that is, the glossiness of the spray pattern, can be detected by using a glossiness detector.
[0028] Furthermore, the effect prediction module outputs the predicted effect image data, which specifically includes the following steps:
[0029] a. Set up the spraying process , where n represents the category of the spraying process, and the spraying process includes spraying primer, spraying paint, spraying varnish, etc. For example, when n=1, the category represented is spraying primer, when n=2, the category represented is spraying paint, when n=3, the category represented is spraying varnish, and i represents the number of spraying processes of each category. n and i are natural numbers and are initially 1;
[0030] b. Obtain spraying data and spraying surface data, input into the spraying effect prediction model, and obtain corresponding effect image data;
[0031] c. Visually displaying the effect image data on the three-dimensional model of the spraying surface, and the user determines whether the visualized effect image data meets the requirements through the spraying effect visualization module;
[0032] d. If yes, update n, set n=n+1, replace the paint sprayed by the spraying module with the paint sprayed by the spraying process corresponding to the updated n, and then control the spraying module to spray;
[0033] e. Otherwise, update i, set i=i+1, and directly control the spraying module to spray again.
[0034] Furthermore, the step b further comprises the following steps:
[0035] Set the glossiness threshold;
[0036] If the spraying process corresponding to this spraying is spraying varnish, then at the end of this spraying, the glossiness data in the effect image data is compared with the glossiness threshold to determine whether the glossiness data is greater than or equal to the glossiness threshold;
[0037] If not, update i, set i=i+1, control the spraying module to spray again, and repeat step b; if yes, proceed to the next step, i.e., step c.
[0038] A method for simulating the effect of automobile spraying at a user end based on big data, comprising the following steps:
[0039] Test the effect image data of the spraying module under different spraying data and spraying surface data to obtain a sample data set;
[0040] Screening the sample data set to obtain a training sample data set, wherein the training sample data set includes spraying training data and spraying surface training data;
[0041] Based on the training sample data and the sample data set, respectively, machine learning models are selected for training, and a trajectory prediction model for predicting the spraying trajectory based on the input spraying surface data, and a spraying effect prediction model for predicting the effect image data based on the input spraying data and the spraying surface data are obtained respectively;
[0042] Acquire the spray surface data of the vehicle to be sprayed, and input the spray surface data into the trajectory prediction model to obtain the spray trajectory;
[0043] Input the spraying data constituting the spraying trajectory and the spraying surface data into the spraying effect prediction model to predict the effect image data;
[0044] The spray surface data is visualized as a three-dimensional model of the spray surface, and the predicted effect image data is visualized on the surface of the three-dimensional model of the spray surface. Based on the spray surface data, set standards and the results of the visualization display, it is judged whether the spraying meets the standards. If it does not meet the standards, spray again until it meets the standards.
[0045] 1. Compared with the prior art, the present invention provides a user-end automobile spraying effect simulation system and method based on big data. By setting a spraying module, a spraying control module, a spraying surface data acquisition module, a spraying monitoring module, and a trajectory generation module, the spraying module can collect the effect image data of different spraying data such as spraying distance, spraying angle, spraying discharge speed, and spraying moving direction through testing, and screen out the spraying data and spraying surface data corresponding to the effect image data with suitable effect images to train a machine learning model, analyze the correspondence between the spraying surface data and the spraying data when the effect image is suitable, and predict the spraying trajectory formed by the spraying data changing over time based on the spraying surface data through the trained machine learning model, so as to facilitate the control of the spraying module to spray according to the spraying trajectory and ensure the spraying effect.
[0046] 2. Compared with the prior art, the present invention provides a big data user-side automobile spraying effect simulation system and method, which establishes a spraying effect prediction model by setting a spraying effect prediction module and a spraying effect visualization module, and analyzing the relationship between spraying data, spraying surface data and spraying effect data. The spraying effect data of each spraying can be predicted through the spraying data and spraying surface data, and visualized, which makes it convenient to decide whether to continue spraying according to the spraying effect, thereby further improving the final effect of spraying. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0048] Figure 1 A system structure block diagram provided for an embodiment of the present invention;
[0049] Figure 2 A schematic diagram of the method steps provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0050] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.
[0051] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.
[0052] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. In addition, 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 a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0053] Example embodiments will be described more fully below with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. On the contrary, the purpose of providing these embodiments is to make the present disclosure thorough and complete and to enable those skilled in the art to fully understand the scope of the present disclosure.
[0054] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.
[0055] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.
[0056] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded.
[0057] The embodiments described herein may be described with reference to plan views and / or cross-sectional views by means of idealized schematic diagrams of the present disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings have schematic properties, and the shapes of the regions shown in the figures illustrate the specific shapes of the regions of the elements, but are not intended to be limiting.
[0058] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined as such herein.
[0059] See also Figure 1-Figure 2 , a big data user-side automobile spraying use effect simulation system, including a spraying module, a spraying control module, a spraying surface data acquisition module, a spraying monitoring module, a trajectory generation module, a spraying effect prediction module, and a spraying effect visualization module;
[0060] The spraying module is used to spray the paint onto the spraying surface of the car, wherein the spraying module can adopt an air spray gun, a high-pressure airless spray gun, an air-assisted spray gun, a portable electrostatic spray gun, etc.;
[0061] The spray control module is used to control the spray distance, spray angle, spray discharge speed, and spray movement direction of the spray module; the spray module can be controlled by setting electric slide rails, motors and other devices, and editing the PLC program;
[0062] The spray surface data acquisition module is used to obtain the surface shape data of the car that needs to be sprayed, obtain the spray surface data, and generate a three-dimensional model of the spray surface based on the spray surface data; the surface shape data of the car that needs to be sprayed can be obtained by scanning or data importing. The scanning spray surface data acquisition module obtains the spray surface data by scanning and detection, which specifically includes the following steps:
[0063] Taking images of the vehicle and the position of the vehicle that needs to be sprayed to obtain a vehicle image;
[0064] Based on the image recognition algorithm, the vehicle image is analyzed to identify the vehicle model and the location that needs to be sprayed;
[0065] Detect whether the spray surface data acquisition module stores the spray surface data and the spray surface three-dimensional model of the corresponding position of the vehicle of the corresponding vehicle model;
[0066] If yes, the corresponding spray surface data and the spray surface three-dimensional model are exported, and the spray surface data are exported and input into the trajectory generation module and the spray effect prediction module, and used as the input of the trajectory prediction model and the spray effect prediction model respectively;
[0067] If not, scan the surface of the car that needs to be sprayed to obtain the sprayed surface data and the corresponding sprayed surface three-dimensional model. The sprayed surface data can be obtained by scanning the car surface through laser scanning, depth camera, etc., and the corresponding sprayed surface three-dimensional model is generated.
[0068] The spray surface data acquisition module is also used to obtain the effect image data of the spray pattern sprayed by the spray module on the spray surface, and associate the effect image data with the corresponding spray surface data, wherein the effect image data includes the shape, size, and color depth of each position of the spray pattern, wherein the color depth of each position is used to judge the uniformity of spraying and the coating thickness of each position of the spray pattern, and the association relationship between the data can be established through the SQL tool;
[0069] The spray surface data acquisition module is also used to save the spray surface data and the spray surface three-dimensional model, and associate the spray surface data and its corresponding spray surface three-dimensional model with the corresponding position of the vehicle of the corresponding vehicle model.
[0070] The spray monitoring module is used to monitor the spray position, moving speed, spray angle, and spray discharge speed of the spray module, obtain spray data, and associate the spray data with the corresponding effect image data. The spray monitoring module can be composed of multiple sensors, and sensors with corresponding functions can be selected and set according to monitoring needs to realize the monitoring of the spray position, moving speed, spray angle, and spray discharge speed. The spray discharge speed is obtained by monitoring the amount of paint sprayed per unit time;
[0071] The trajectory generation module is used to train a first machine learning model based on the spraying data and the spraying surface data to obtain a trajectory prediction model, which is used to obtain a predicted spraying trajectory based on the input spraying surface data. The spraying trajectory is a spraying data set composed of the spraying data changing over time. The present invention does not limit the specific machine learning model, and can be selected according to the actual needs during training, such as a regression model, a support vector machine model, a random forest model, a convolutional neural network, etc., and multiple models can be selected at the same time for combined use and training.
[0072] The trajectory generation module trains the first machine learning model, specifically including the following steps:
[0073] Obtaining an effect image corresponding to the effect image data;
[0074] Screening effect images that meet the standards from the effect images, and acquiring corresponding effect image data to obtain effect image training data;
[0075] Retrieving the spray surface data associated with the effect image training data to obtain the spray surface training data, and retrieving the spraying data associated with the spray surface training data to obtain the spraying training data;
[0076] Based on the spraying training data and the spraying surface training data, a first machine learning model is trained to obtain a trajectory prediction model. How to use data to train the model is common knowledge in the prior art and is directly applied without any changes. Therefore, it is not described in detail in this technical solution, and it will not cause trouble to this technical solution based on the field. When the accuracy of the trained machine learning model reaches the set threshold, the parameters of the machine learning model at this time are determined to obtain the corresponding trajectory prediction model or spraying effect prediction model.
[0077] The spraying effect prediction module is used to train the second machine learning model based on the spraying data, the spraying surface data, and the effect image data to obtain the spraying effect prediction model, which is used to output the predicted effect image data based on the input spraying data and the spraying surface data; because in the actual automobile painting spraying operation, it is usually necessary to spray a layer of primer first, and then spray the paint. The paint may need to be sprayed multiple times to ensure sufficient coverage of the paint and uniform color. Finally, spray multiple layers of clear varnish to ensure sufficient protection of the coating and to ensure the gloss of the coating. At this time, the spraying effect prediction model can be used to predict the spraying effect after each spraying, that is, the effect image data, to check whether the gloss of the sprayed coating meets the requirements.
[0078] The spraying effect visualization module is used to visualize the predicted effect image data on the three-dimensional model of the spraying surface.
[0079] The effect image data collected by the spray surface data collection module also includes the glossiness data of the spray pattern. The glossiness of the spray surface after spraying, that is, the glossiness of the spray pattern, can be detected by using a glossiness detector.
[0080] The effect prediction module outputs the predicted effect image data, which specifically includes the following steps:
[0081] a. Set up the spraying process , where n represents the category of the spraying process, which includes spraying primer, spraying paint, spraying varnish, etc. For example, when n=1, the category represented is spraying primer, when n=2, the category represented is spraying paint, when n=3, the category represented is spraying varnish, and i represents the number of spraying processes of each category. n and i are natural numbers and are initially 1;
[0082] b. Obtain spraying data and spraying surface data, input into the spraying effect prediction model, and obtain corresponding effect image data;
[0083] In one embodiment, the following steps are also included:
[0084] Set the glossiness threshold;
[0085] If the spraying process corresponding to this spraying is spraying varnish, then at the end of this spraying, the glossiness data in the effect image data is compared with the glossiness threshold to determine whether the glossiness data is greater than or equal to the glossiness threshold;
[0086] If not, update i, set i=i+1, control the spraying module to spray again, and repeat step b; if yes, proceed to the next step, i.e., step c.
[0087] c. Visualize the effect image data on the three-dimensional model of the spraying surface, and the user judges whether the visualized effect image data meets the requirements through the spraying effect visualization module;
[0088] d. If yes, update n, set n=n+1, replace the paint sprayed by the spraying module with the paint sprayed by the spraying process corresponding to the updated n, and then control the spraying module to spray;
[0089] e. Otherwise, update i, set i=i+1, and directly control the spraying module to spray again.
[0090] A method for simulating the effect of automobile spraying at a user end based on big data, comprising the following steps:
[0091] Test the effect image data of the spraying module under different spraying data and spraying surface data to obtain a sample data set;
[0092] The sample data set is screened to obtain a training sample data set, where the training sample data set includes spraying training data and spraying surface training data;
[0093] Based on the training sample data and the sample data set, respectively, machine learning models are selected for training, and a trajectory prediction model for predicting the spraying trajectory based on the input spraying surface data, and a spraying effect prediction model for predicting the effect image data based on the input spraying data and the spraying surface data are obtained respectively;
[0094] Acquire the spray surface data of the vehicle to be sprayed, and input the spray surface data into the trajectory prediction model to obtain the spray trajectory;
[0095] Input the spraying data constituting the spraying trajectory and the spraying surface data into the spraying effect prediction model to predict the effect image data;
[0096] The spray surface data is visualized as a three-dimensional model of the spray surface, and the predicted effect image data is visualized on the surface of the three-dimensional model of the spray surface. Based on the spray surface data, set standards and the results of the visualization display, it is judged whether the spraying meets the standards. If it does not meet the standards, spray again until it meets the standards.
[0097] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.
Claims
1. A big data user-side automobile spraying effect simulation system, characterized by: It includes a spraying module, a spraying control module, a spraying surface data acquisition module, a spraying monitoring module, a trajectory generation module, a spraying effect prediction module, and a spraying effect visualization module; The spraying module is used to spray paint onto the spraying surface of the car; The spray control module is used to control the spray distance, spray angle, spray discharge speed and spray movement direction of the spray module; The spray surface data acquisition module is used to obtain the surface shape data of the automobile to be sprayed, obtain the spray surface data, and generate a three-dimensional model of the spray surface based on the spray surface data; The spray surface data acquisition module is also used to obtain effect image data of the spray pattern sprayed by the spray module onto the spray surface, and associate the effect image data with the corresponding spray surface data; The spray monitoring module is used to monitor the spray position, moving speed, spray angle, and spray discharge speed of the spray module, obtain spray data, and associate the spray data with the corresponding effect image data; The trajectory generation module is used to train a first machine learning model based on the spraying data and the spraying surface data to obtain a trajectory prediction model, which is used to obtain a predicted spraying trajectory based on the input spraying surface data, wherein the spraying trajectory is a spraying data set composed of spraying data changing over time; The spraying effect prediction module is used to train a second machine learning model based on the spraying data, the spraying surface data, and the effect image data to obtain a spraying effect prediction model, and is used to output predicted effect image data based on the input spraying data and the spraying surface data; The spraying effect visualization module is used to visualize the predicted effect image data on the three-dimensional model of the spraying surface; The trajectory generation module trains the first machine learning model, specifically comprising the following steps: Obtaining an effect image corresponding to the effect image data; Screening effect images that meet the standards from the effect images, and acquiring corresponding effect image data to obtain effect image training data; Retrieving the spray surface data associated with the effect image training data to obtain the spray surface training data, and retrieving the spraying data associated with the spray surface training data to obtain the spraying training data; Based on the spraying training data and the spraying surface training data, a first machine learning model is trained to obtain a trajectory prediction model.
2. According to the big data user-side automobile spraying effect simulation system of claim 1, it is characterized by: The spray surface data acquisition module is also used to save the spray surface data and the spray surface three-dimensional model, and associate the spray surface data and its corresponding spray surface three-dimensional model with the corresponding position of the vehicle of the corresponding vehicle model.
3. According to the big data user-side automobile spraying effect simulation system of claim 2, it is characterized by: The spray surface data acquisition module obtains the spray surface data by scanning and detecting, which specifically includes the following steps: Taking images of the vehicle and the position of the vehicle that needs to be sprayed to obtain a vehicle image; Based on the image recognition algorithm, the vehicle image is analyzed to identify the vehicle model and the location that needs to be sprayed; Detect whether the spray surface data acquisition module stores the spray surface data and the spray surface three-dimensional model of the corresponding position of the vehicle of the corresponding vehicle model; If yes, the corresponding spray surface data and the spray surface three-dimensional model are exported; If not, scan the surface of the car that needs to be sprayed to obtain the sprayed surface data and the corresponding sprayed surface three-dimensional model.
4. According to the big data user-side automobile spraying effect simulation system of claim 1, it is characterized by: The effect image data collected by the spray surface data collection module also includes glossiness data of the spray pattern.
5. According to the big data user-side automobile spraying effect simulation system of claim 2, it is characterized by: The effect prediction module outputs predicted effect image data, specifically comprising the following steps: a. Set up the spraying process , where n represents the category of the spraying process, and the spraying process includes spraying primer, spraying paint, and spraying varnish, i represents the number of spraying processes of each category, and n and i are natural numbers and are initially 1; b. Obtain spraying data and spraying surface data, input into the spraying effect prediction model, and obtain corresponding effect image data; c. Visually displaying the effect image data on the three-dimensional model of the spraying surface, and the user determines whether the visualized effect image data meets the requirements through the spraying effect visualization module; d. If yes, update n, set n=n+1, replace the paint sprayed by the spraying module with the paint sprayed by the spraying process corresponding to the updated n, and then control the spraying module to spray; e. Otherwise, update i, set i=i+1, and directly control the spraying module to spray again.
6. The big data user-side automobile spraying effect simulation system according to claim 5 is characterized by: The step b further comprises the following steps: Set the glossiness threshold; If the spraying process corresponding to this spraying is spraying varnish, then at the end of this spraying, the glossiness data in the effect image data is compared with the glossiness threshold to determine whether the glossiness data is greater than or equal to the glossiness threshold; If not, update i, set i=i+1, control the spraying module to spray again, and repeat step b.
7. A method for simulating the effect of automobile spraying at the user end of big data, applicable to a system for simulating the effect of automobile spraying at the user end of big data according to any one of claims 1 to 6, characterized in that: The following steps are involved: Test the effect image data of the spraying module under different spraying data and spraying surface data to obtain a sample data set; Screening the sample data set to obtain a training sample data set, wherein the training sample data set includes spraying training data and spraying surface training data; Based on the training sample data and the sample data set, respectively, machine learning models are selected for training, and a trajectory prediction model for predicting the spraying trajectory based on the input spraying surface data and a spraying effect prediction model for predicting the effect image data based on the input spraying data and the spraying surface data are obtained respectively; Acquire the spray surface data of the vehicle to be sprayed, and input the spray surface data into the trajectory prediction model to obtain the spray trajectory; Input the spraying data constituting the spraying trajectory and the spraying surface data into the spraying effect prediction model to predict the effect image data; The spray surface data is visualized as a three-dimensional model of the spray surface, and the predicted effect image data is visualized on the surface of the three-dimensional model of the spray surface. Based on the spray surface data, set standards and the results of the visualization display, it is judged whether the spraying meets the standards. If it does not meet the standards, spray again until it meets the standards.
